Model save

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: cc-by-nc-4.0
+base_model: MCG-NJU/videomae-base
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: VideoMAE_wlasl__codeCheck
+  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. -->
+
+# VideoMAE_wlasl__codeCheck
+
+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: 7.6141
+- Accuracy: 0.0010
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 1786
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 30.6603       | 1.0   | 1786 | 7.6141          | 0.0010   |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.1

trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.0010214504596527069,
+  "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/VideoMAE_wlasl__codeCheck/checkpoint-1786",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1786,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 20.611459732055664,
+      "learning_rate": 1.2445550715619166e-07,
+      "loss": 30.6603,
+      "step": 1786
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.0010214504596527069,
+      "eval_loss": 7.61414909362793,
+      "eval_runtime": 297.8226,
+      "eval_samples_per_second": 13.149,
+      "eval_steps_per_second": 6.574,
+      "step": 1786
+    },
+    {
+      "epoch": 1.0,
+      "step": 1786,
+      "total_flos": 1.8121006360874189e+19,
+      "train_loss": 30.660261233202686,
+      "train_runtime": 1787.4428,
+      "train_samples_per_second": 7.994,
+      "train_steps_per_second": 0.999
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1786,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8121006360874189e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}