End of training
Browse files
README.md
CHANGED
|
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [facebook/convnextv2-nano-22k-384](https://huggingface.co/facebook/convnextv2-nano-22k-384) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Accuracy: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [facebook/convnextv2-nano-22k-384](https://huggingface.co/facebook/convnextv2-nano-22k-384) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8620
|
| 21 |
+
- Accuracy: 0.775
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 5.091978035331072e+16,
|
| 4 |
+
"train_loss": 1.3109167098999024,
|
| 5 |
+
"train_runtime": 32.3348,
|
| 6 |
+
"train_samples_per_second": 39.586,
|
| 7 |
+
"train_steps_per_second": 0.619
|
| 8 |
+
}
|
runs/May23_15-24-25_d5de458e9752/events.out.tfevents.1716478667.d5de458e9752.34.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0991b9273fd2b600d2248cd4ecf20c26b41fce4da081d2f5df10fe2c94cd8783
|
| 3 |
+
size 405
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.0,
|
| 3 |
+
"total_flos": 5.091978035331072e+16,
|
| 4 |
+
"train_loss": 1.3109167098999024,
|
| 5 |
+
"train_runtime": 32.3348,
|
| 6 |
+
"train_samples_per_second": 39.586,
|
| 7 |
+
"train_steps_per_second": 0.619
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9655162692070007,
|
| 3 |
+
"best_model_checkpoint": "./test-augment/checkpoint-20",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 20,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.6375,
|
| 14 |
+
"eval_loss": 1.1256365776062012,
|
| 15 |
+
"eval_runtime": 1.0412,
|
| 16 |
+
"eval_samples_per_second": 76.836,
|
| 17 |
+
"eval_steps_per_second": 1.921,
|
| 18 |
+
"step": 10
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_accuracy": 0.7125,
|
| 23 |
+
"eval_loss": 0.9655162692070007,
|
| 24 |
+
"eval_runtime": 1.0636,
|
| 25 |
+
"eval_samples_per_second": 75.217,
|
| 26 |
+
"eval_steps_per_second": 1.88,
|
| 27 |
+
"step": 20
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.0,
|
| 31 |
+
"step": 20,
|
| 32 |
+
"total_flos": 5.091978035331072e+16,
|
| 33 |
+
"train_loss": 1.3109167098999024,
|
| 34 |
+
"train_runtime": 32.3348,
|
| 35 |
+
"train_samples_per_second": 39.586,
|
| 36 |
+
"train_steps_per_second": 0.619
|
| 37 |
+
}
|
| 38 |
+
],
|
| 39 |
+
"logging_steps": 100,
|
| 40 |
+
"max_steps": 20,
|
| 41 |
+
"num_input_tokens_seen": 0,
|
| 42 |
+
"num_train_epochs": 2,
|
| 43 |
+
"save_steps": 500,
|
| 44 |
+
"total_flos": 5.091978035331072e+16,
|
| 45 |
+
"train_batch_size": 64,
|
| 46 |
+
"trial_name": null,
|
| 47 |
+
"trial_params": null
|
| 48 |
+
}
|