Training in progress, epoch 0

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,64 @@
+---
+license: cc-by-nc-4.0
+base_model: facebook/timesformer-base-finetuned-k400
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: timesformer-base-finetuned-k400-finetuned-ucf101-subset
+  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. -->
+
+# timesformer-base-finetuned-k400-finetuned-ucf101-subset
+
+This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0878
+- Accuracy: 1.0
+
+## 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: 6
+- eval_batch_size: 6
+- 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: 200
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.1523        | 0.25  | 50   | 0.0735          | 1.0      |
+| 0.024         | 1.25  | 100  | 0.0470          | 0.9866   |
+| 0.0583        | 2.25  | 150  | 0.0302          | 0.9866   |
+| 0.0036        | 3.25  | 200  | 0.0297          | 0.9866   |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.19.1
+- Tokenizers 0.19.1

.ipynb_checkpoints/all_results-checkpoint.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.25,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.08780594170093536,
+    "eval_runtime": 76.2242,
+    "eval_samples_per_second": 4.552,
+    "eval_steps_per_second": 0.761
+}

.ipynb_checkpoints/test_results-checkpoint.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.25,
+    "eval_accuracy": 1.0,
+    "eval_loss": 0.08780594170093536,
+    "eval_runtime": 76.2242,
+    "eval_samples_per_second": 4.552,
+    "eval_steps_per_second": 0.761
+}

.ipynb_checkpoints/trainer_state-checkpoint.json

@@ -0,0 +1,224 @@
+{
+  "best_metric": 1.0,
+  "best_model_checkpoint": "timesformer-base-finetuned-k400-finetuned-ucf101-subset/checkpoint-50",
+  "epoch": 3.25,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "grad_norm": 14.361767768859863,
+      "learning_rate": 2.5e-05,
+      "loss": 2.3816,
+      "step": 10
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 8.448980331420898,
+      "learning_rate": 5e-05,
+      "loss": 1.5686,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 7.0012526512146,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.6191,
+      "step": 30
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 4.961479187011719,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.3468,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.13403058052063,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.1523,
+      "step": 50
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.07354684174060822,
+      "eval_runtime": 34.9344,
+      "eval_samples_per_second": 4.265,
+      "eval_steps_per_second": 0.716,
+      "step": 50
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.933645486831665,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.0521,
+      "step": 60
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.865109920501709,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 0.0226,
+      "step": 70
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.17869924008846283,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.108,
+      "step": 80
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.23531177639961243,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.0107,
+      "step": 90
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.1640271246433258,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.024,
+      "step": 100
+    },
+    {
+      "epoch": 1.25,
+      "eval_accuracy": 0.9865771812080537,
+      "eval_loss": 0.046999599784612656,
+      "eval_runtime": 32.3832,
+      "eval_samples_per_second": 4.601,
+      "eval_steps_per_second": 0.772,
+      "step": 100
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.47139155864715576,
+      "learning_rate": 2.5e-05,
+      "loss": 0.0056,
+      "step": 110
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.11248086392879486,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.0045,
+      "step": 120
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.07324650138616562,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 0.0042,
+      "step": 130
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.46895766258239746,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.0202,
+      "step": 140
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.048765964806079865,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.0583,
+      "step": 150
+    },
+    {
+      "epoch": 2.25,
+      "eval_accuracy": 0.9865771812080537,
+      "eval_loss": 0.030154313892126083,
+      "eval_runtime": 32.7398,
+      "eval_samples_per_second": 4.551,
+      "eval_steps_per_second": 0.764,
+      "step": 150
+    },
+    {
+      "epoch": 3.05,
+      "grad_norm": 0.11046731472015381,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.0032,
+      "step": 160
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.07638247311115265,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.0027,
+      "step": 170
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 0.0314478874206543,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.0053,
+      "step": 180
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.23283490538597107,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.0032,
+      "step": 190
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.3815344274044037,
+      "learning_rate": 0.0,
+      "loss": 0.0036,
+      "step": 200
+    },
+    {
+      "epoch": 3.25,
+      "eval_accuracy": 0.9865771812080537,
+      "eval_loss": 0.02967873215675354,
+      "eval_runtime": 32.6048,
+      "eval_samples_per_second": 4.57,
+      "eval_steps_per_second": 0.767,
+      "step": 200
+    },
+    {
+      "epoch": 3.25,
+      "step": 200,
+      "total_flos": 1.0514301109272576e+18,
+      "train_loss": 0.2698267618194222,
+      "train_runtime": 1064.2955,
+      "train_samples_per_second": 1.128,
+      "train_steps_per_second": 0.188
+    },
+    {
+      "epoch": 3.25,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.08780594170093536,
+      "eval_runtime": 86.4118,
+      "eval_samples_per_second": 4.016,
+      "eval_steps_per_second": 0.671,
+      "step": 200
+    },
+    {
+      "epoch": 3.25,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.08780594170093536,
+      "eval_runtime": 76.2242,
+      "eval_samples_per_second": 4.552,
+      "eval_steps_per_second": 0.761,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9223372036854775807,
+  "save_steps": 500,
+  "total_flos": 1.0514301109272576e+18,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9376ab61570e92ddbc75657778a029c7977423294333a9d8b7544c679041f40c
+oid sha256:ba7066ff06eb97588768c310562feeabbebd4dae8f1b19069cb3365f54df0caa
 size 485096872

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0976022ff1e3e4b6c6ed3d4b9f4fbf236be50b91b6fc1edad006409b3e04fd11
+oid sha256:0227df48b0d08dff9e4610c246ea0c33f3bdb212835acc291f35432a21b34467
 size 5048