Upload 8 files
Browse files- config.json +54 -0
- optimizer.pt +3 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +709 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/bit-50",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BitForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"conv_layer": "std_conv",
|
| 7 |
+
"depths": [
|
| 8 |
+
3,
|
| 9 |
+
4,
|
| 10 |
+
6,
|
| 11 |
+
3
|
| 12 |
+
],
|
| 13 |
+
"drop_path_rate": 0.0,
|
| 14 |
+
"embedding_dynamic_padding": false,
|
| 15 |
+
"embedding_size": 64,
|
| 16 |
+
"global_padding": null,
|
| 17 |
+
"hidden_act": "relu",
|
| 18 |
+
"hidden_sizes": [
|
| 19 |
+
256,
|
| 20 |
+
512,
|
| 21 |
+
1024,
|
| 22 |
+
2048
|
| 23 |
+
],
|
| 24 |
+
"id2label": {
|
| 25 |
+
"0": "Abnormal",
|
| 26 |
+
"1": "Normal"
|
| 27 |
+
},
|
| 28 |
+
"label2id": {
|
| 29 |
+
"Abnormal": 0,
|
| 30 |
+
"Normal": 1
|
| 31 |
+
},
|
| 32 |
+
"layer_type": "preactivation",
|
| 33 |
+
"model_type": "bit",
|
| 34 |
+
"num_channels": 3,
|
| 35 |
+
"num_groups": 32,
|
| 36 |
+
"out_features": [
|
| 37 |
+
"stage4"
|
| 38 |
+
],
|
| 39 |
+
"out_indices": [
|
| 40 |
+
4
|
| 41 |
+
],
|
| 42 |
+
"output_stride": 32,
|
| 43 |
+
"problem_type": "single_label_classification",
|
| 44 |
+
"stage_names": [
|
| 45 |
+
"stem",
|
| 46 |
+
"stage1",
|
| 47 |
+
"stage2",
|
| 48 |
+
"stage3",
|
| 49 |
+
"stage4"
|
| 50 |
+
],
|
| 51 |
+
"torch_dtype": "float32",
|
| 52 |
+
"transformers_version": "4.31.0",
|
| 53 |
+
"width_factor": 1
|
| 54 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2efc9aab2d9259e66e7d21e130f5394e2ba8c4b0ccec1dd4f5f0dc62fee4517
|
| 3 |
+
size 188126085
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 448,
|
| 4 |
+
"width": 448
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "BitImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.5,
|
| 19 |
+
0.5,
|
| 20 |
+
0.5
|
| 21 |
+
],
|
| 22 |
+
"resample": 2,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"shortest_edge": 448
|
| 26 |
+
}
|
| 27 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca0692a75ae4a303f501ee413a274d6497b3d3f7abeb42d054c17cc585e02e35
|
| 3 |
+
size 94069425
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bc8719f13dfe5e12bbd1fccb006d5641c3f633b317e9e0a27e9c4771147a072
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da0b5e53050decaada047b8bc10e06f60dc17b093dedb9ff2142f40c279d2900
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,709 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "bit-50-Otitis-binary\\checkpoint-312",
|
| 4 |
+
"epoch": 46.15384615384615,
|
| 5 |
+
"global_step": 450,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.92,
|
| 12 |
+
"eval_accuracy": 0.6142857142857143,
|
| 13 |
+
"eval_loss": 0.828590989112854,
|
| 14 |
+
"eval_runtime": 1.3305,
|
| 15 |
+
"eval_samples_per_second": 52.613,
|
| 16 |
+
"eval_steps_per_second": 3.758,
|
| 17 |
+
"step": 9
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 1.03,
|
| 21 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 22 |
+
"loss": 0.9957,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.95,
|
| 27 |
+
"eval_accuracy": 0.6714285714285714,
|
| 28 |
+
"eval_loss": 0.5884611010551453,
|
| 29 |
+
"eval_runtime": 0.9182,
|
| 30 |
+
"eval_samples_per_second": 76.24,
|
| 31 |
+
"eval_steps_per_second": 5.446,
|
| 32 |
+
"step": 19
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.05,
|
| 36 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 37 |
+
"loss": 0.6913,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.97,
|
| 42 |
+
"eval_accuracy": 0.8,
|
| 43 |
+
"eval_loss": 0.4655839502811432,
|
| 44 |
+
"eval_runtime": 0.9168,
|
| 45 |
+
"eval_samples_per_second": 76.355,
|
| 46 |
+
"eval_steps_per_second": 5.454,
|
| 47 |
+
"step": 29
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.08,
|
| 51 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 52 |
+
"loss": 0.5636,
|
| 53 |
+
"step": 30
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.0,
|
| 57 |
+
"eval_accuracy": 0.7142857142857143,
|
| 58 |
+
"eval_loss": 0.5395815372467041,
|
| 59 |
+
"eval_runtime": 0.9219,
|
| 60 |
+
"eval_samples_per_second": 75.926,
|
| 61 |
+
"eval_steps_per_second": 5.423,
|
| 62 |
+
"step": 39
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.1,
|
| 66 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 67 |
+
"loss": 0.5036,
|
| 68 |
+
"step": 40
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.92,
|
| 72 |
+
"eval_accuracy": 0.8714285714285714,
|
| 73 |
+
"eval_loss": 0.31175073981285095,
|
| 74 |
+
"eval_runtime": 0.9263,
|
| 75 |
+
"eval_samples_per_second": 75.568,
|
| 76 |
+
"eval_steps_per_second": 5.398,
|
| 77 |
+
"step": 48
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 5.13,
|
| 81 |
+
"learning_rate": 4.938271604938271e-05,
|
| 82 |
+
"loss": 0.4238,
|
| 83 |
+
"step": 50
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.95,
|
| 87 |
+
"eval_accuracy": 0.7714285714285715,
|
| 88 |
+
"eval_loss": 0.500621497631073,
|
| 89 |
+
"eval_runtime": 0.962,
|
| 90 |
+
"eval_samples_per_second": 72.767,
|
| 91 |
+
"eval_steps_per_second": 5.198,
|
| 92 |
+
"step": 58
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.15,
|
| 96 |
+
"learning_rate": 4.814814814814815e-05,
|
| 97 |
+
"loss": 0.4115,
|
| 98 |
+
"step": 60
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.97,
|
| 102 |
+
"eval_accuracy": 0.8571428571428571,
|
| 103 |
+
"eval_loss": 0.30729931592941284,
|
| 104 |
+
"eval_runtime": 0.9315,
|
| 105 |
+
"eval_samples_per_second": 75.145,
|
| 106 |
+
"eval_steps_per_second": 5.367,
|
| 107 |
+
"step": 68
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 7.18,
|
| 111 |
+
"learning_rate": 4.691358024691358e-05,
|
| 112 |
+
"loss": 0.3887,
|
| 113 |
+
"step": 70
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 8.0,
|
| 117 |
+
"eval_accuracy": 0.8714285714285714,
|
| 118 |
+
"eval_loss": 0.2601815164089203,
|
| 119 |
+
"eval_runtime": 0.9413,
|
| 120 |
+
"eval_samples_per_second": 74.368,
|
| 121 |
+
"eval_steps_per_second": 5.312,
|
| 122 |
+
"step": 78
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 8.21,
|
| 126 |
+
"learning_rate": 4.567901234567901e-05,
|
| 127 |
+
"loss": 0.3072,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.92,
|
| 132 |
+
"eval_accuracy": 0.8285714285714286,
|
| 133 |
+
"eval_loss": 0.2863541543483734,
|
| 134 |
+
"eval_runtime": 0.9861,
|
| 135 |
+
"eval_samples_per_second": 70.987,
|
| 136 |
+
"eval_steps_per_second": 5.071,
|
| 137 |
+
"step": 87
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 9.23,
|
| 141 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 142 |
+
"loss": 0.414,
|
| 143 |
+
"step": 90
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 9.95,
|
| 147 |
+
"eval_accuracy": 0.8714285714285714,
|
| 148 |
+
"eval_loss": 0.3076455593109131,
|
| 149 |
+
"eval_runtime": 0.9303,
|
| 150 |
+
"eval_samples_per_second": 75.243,
|
| 151 |
+
"eval_steps_per_second": 5.374,
|
| 152 |
+
"step": 97
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.26,
|
| 156 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 157 |
+
"loss": 0.2338,
|
| 158 |
+
"step": 100
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.97,
|
| 162 |
+
"eval_accuracy": 0.9571428571428572,
|
| 163 |
+
"eval_loss": 0.14239218831062317,
|
| 164 |
+
"eval_runtime": 0.942,
|
| 165 |
+
"eval_samples_per_second": 74.31,
|
| 166 |
+
"eval_steps_per_second": 5.308,
|
| 167 |
+
"step": 107
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 11.28,
|
| 171 |
+
"learning_rate": 4.197530864197531e-05,
|
| 172 |
+
"loss": 0.2929,
|
| 173 |
+
"step": 110
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 12.0,
|
| 177 |
+
"eval_accuracy": 0.9714285714285714,
|
| 178 |
+
"eval_loss": 0.140659362077713,
|
| 179 |
+
"eval_runtime": 0.9302,
|
| 180 |
+
"eval_samples_per_second": 75.252,
|
| 181 |
+
"eval_steps_per_second": 5.375,
|
| 182 |
+
"step": 117
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 12.31,
|
| 186 |
+
"learning_rate": 4.074074074074074e-05,
|
| 187 |
+
"loss": 0.2749,
|
| 188 |
+
"step": 120
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 12.92,
|
| 192 |
+
"eval_accuracy": 0.9428571428571428,
|
| 193 |
+
"eval_loss": 0.1332792341709137,
|
| 194 |
+
"eval_runtime": 0.9308,
|
| 195 |
+
"eval_samples_per_second": 75.204,
|
| 196 |
+
"eval_steps_per_second": 5.372,
|
| 197 |
+
"step": 126
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 13.33,
|
| 201 |
+
"learning_rate": 3.950617283950617e-05,
|
| 202 |
+
"loss": 0.2115,
|
| 203 |
+
"step": 130
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 13.95,
|
| 207 |
+
"eval_accuracy": 0.9285714285714286,
|
| 208 |
+
"eval_loss": 0.11323489248752594,
|
| 209 |
+
"eval_runtime": 0.926,
|
| 210 |
+
"eval_samples_per_second": 75.595,
|
| 211 |
+
"eval_steps_per_second": 5.4,
|
| 212 |
+
"step": 136
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 14.36,
|
| 216 |
+
"learning_rate": 3.82716049382716e-05,
|
| 217 |
+
"loss": 0.1988,
|
| 218 |
+
"step": 140
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 14.97,
|
| 222 |
+
"eval_accuracy": 0.9571428571428572,
|
| 223 |
+
"eval_loss": 0.10268964618444443,
|
| 224 |
+
"eval_runtime": 0.9214,
|
| 225 |
+
"eval_samples_per_second": 75.969,
|
| 226 |
+
"eval_steps_per_second": 5.426,
|
| 227 |
+
"step": 146
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 15.38,
|
| 231 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 232 |
+
"loss": 0.1931,
|
| 233 |
+
"step": 150
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 16.0,
|
| 237 |
+
"eval_accuracy": 0.9857142857142858,
|
| 238 |
+
"eval_loss": 0.04763292521238327,
|
| 239 |
+
"eval_runtime": 0.9302,
|
| 240 |
+
"eval_samples_per_second": 75.249,
|
| 241 |
+
"eval_steps_per_second": 5.375,
|
| 242 |
+
"step": 156
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 16.41,
|
| 246 |
+
"learning_rate": 3.580246913580247e-05,
|
| 247 |
+
"loss": 0.1597,
|
| 248 |
+
"step": 160
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.92,
|
| 252 |
+
"eval_accuracy": 0.9571428571428572,
|
| 253 |
+
"eval_loss": 0.10970413684844971,
|
| 254 |
+
"eval_runtime": 0.9199,
|
| 255 |
+
"eval_samples_per_second": 76.095,
|
| 256 |
+
"eval_steps_per_second": 5.435,
|
| 257 |
+
"step": 165
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 17.44,
|
| 261 |
+
"learning_rate": 3.45679012345679e-05,
|
| 262 |
+
"loss": 0.1786,
|
| 263 |
+
"step": 170
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 17.95,
|
| 267 |
+
"eval_accuracy": 0.9428571428571428,
|
| 268 |
+
"eval_loss": 0.17402605712413788,
|
| 269 |
+
"eval_runtime": 0.9614,
|
| 270 |
+
"eval_samples_per_second": 72.809,
|
| 271 |
+
"eval_steps_per_second": 5.201,
|
| 272 |
+
"step": 175
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 18.46,
|
| 276 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 277 |
+
"loss": 0.139,
|
| 278 |
+
"step": 180
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 18.97,
|
| 282 |
+
"eval_accuracy": 0.9571428571428572,
|
| 283 |
+
"eval_loss": 0.07017717510461807,
|
| 284 |
+
"eval_runtime": 0.9316,
|
| 285 |
+
"eval_samples_per_second": 75.143,
|
| 286 |
+
"eval_steps_per_second": 5.367,
|
| 287 |
+
"step": 185
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 19.49,
|
| 291 |
+
"learning_rate": 3.209876543209876e-05,
|
| 292 |
+
"loss": 0.1553,
|
| 293 |
+
"step": 190
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 20.0,
|
| 297 |
+
"eval_accuracy": 0.9571428571428572,
|
| 298 |
+
"eval_loss": 0.15834562480449677,
|
| 299 |
+
"eval_runtime": 0.9425,
|
| 300 |
+
"eval_samples_per_second": 74.274,
|
| 301 |
+
"eval_steps_per_second": 5.305,
|
| 302 |
+
"step": 195
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 20.51,
|
| 306 |
+
"learning_rate": 3.08641975308642e-05,
|
| 307 |
+
"loss": 0.1488,
|
| 308 |
+
"step": 200
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 20.92,
|
| 312 |
+
"eval_accuracy": 0.9857142857142858,
|
| 313 |
+
"eval_loss": 0.04526468738913536,
|
| 314 |
+
"eval_runtime": 0.9153,
|
| 315 |
+
"eval_samples_per_second": 76.476,
|
| 316 |
+
"eval_steps_per_second": 5.463,
|
| 317 |
+
"step": 204
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 21.54,
|
| 321 |
+
"learning_rate": 2.962962962962963e-05,
|
| 322 |
+
"loss": 0.1425,
|
| 323 |
+
"step": 210
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 21.95,
|
| 327 |
+
"eval_accuracy": 0.9285714285714286,
|
| 328 |
+
"eval_loss": 0.21590319275856018,
|
| 329 |
+
"eval_runtime": 0.916,
|
| 330 |
+
"eval_samples_per_second": 76.423,
|
| 331 |
+
"eval_steps_per_second": 5.459,
|
| 332 |
+
"step": 214
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 22.56,
|
| 336 |
+
"learning_rate": 2.839506172839506e-05,
|
| 337 |
+
"loss": 0.1716,
|
| 338 |
+
"step": 220
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 22.97,
|
| 342 |
+
"eval_accuracy": 0.9857142857142858,
|
| 343 |
+
"eval_loss": 0.03548683598637581,
|
| 344 |
+
"eval_runtime": 0.9262,
|
| 345 |
+
"eval_samples_per_second": 75.579,
|
| 346 |
+
"eval_steps_per_second": 5.399,
|
| 347 |
+
"step": 224
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 23.59,
|
| 351 |
+
"learning_rate": 2.7160493827160493e-05,
|
| 352 |
+
"loss": 0.0913,
|
| 353 |
+
"step": 230
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 24.0,
|
| 357 |
+
"eval_accuracy": 0.9857142857142858,
|
| 358 |
+
"eval_loss": 0.026874909177422523,
|
| 359 |
+
"eval_runtime": 0.9611,
|
| 360 |
+
"eval_samples_per_second": 72.836,
|
| 361 |
+
"eval_steps_per_second": 5.203,
|
| 362 |
+
"step": 234
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 24.62,
|
| 366 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 367 |
+
"loss": 0.1076,
|
| 368 |
+
"step": 240
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 24.92,
|
| 372 |
+
"eval_accuracy": 0.9857142857142858,
|
| 373 |
+
"eval_loss": 0.0271690022200346,
|
| 374 |
+
"eval_runtime": 0.9105,
|
| 375 |
+
"eval_samples_per_second": 76.881,
|
| 376 |
+
"eval_steps_per_second": 5.491,
|
| 377 |
+
"step": 243
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 25.64,
|
| 381 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 382 |
+
"loss": 0.1083,
|
| 383 |
+
"step": 250
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 25.95,
|
| 387 |
+
"eval_accuracy": 0.9857142857142858,
|
| 388 |
+
"eval_loss": 0.0268684271723032,
|
| 389 |
+
"eval_runtime": 0.9263,
|
| 390 |
+
"eval_samples_per_second": 75.573,
|
| 391 |
+
"eval_steps_per_second": 5.398,
|
| 392 |
+
"step": 253
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 26.67,
|
| 396 |
+
"learning_rate": 2.345679012345679e-05,
|
| 397 |
+
"loss": 0.1002,
|
| 398 |
+
"step": 260
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 26.97,
|
| 402 |
+
"eval_accuracy": 0.9857142857142858,
|
| 403 |
+
"eval_loss": 0.04236455634236336,
|
| 404 |
+
"eval_runtime": 0.9254,
|
| 405 |
+
"eval_samples_per_second": 75.641,
|
| 406 |
+
"eval_steps_per_second": 5.403,
|
| 407 |
+
"step": 263
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 27.69,
|
| 411 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 412 |
+
"loss": 0.1344,
|
| 413 |
+
"step": 270
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 28.0,
|
| 417 |
+
"eval_accuracy": 0.9857142857142858,
|
| 418 |
+
"eval_loss": 0.027010390534996986,
|
| 419 |
+
"eval_runtime": 0.9149,
|
| 420 |
+
"eval_samples_per_second": 76.508,
|
| 421 |
+
"eval_steps_per_second": 5.465,
|
| 422 |
+
"step": 273
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 28.72,
|
| 426 |
+
"learning_rate": 2.0987654320987655e-05,
|
| 427 |
+
"loss": 0.1223,
|
| 428 |
+
"step": 280
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 28.92,
|
| 432 |
+
"eval_accuracy": 0.9857142857142858,
|
| 433 |
+
"eval_loss": 0.0340094119310379,
|
| 434 |
+
"eval_runtime": 0.9259,
|
| 435 |
+
"eval_samples_per_second": 75.599,
|
| 436 |
+
"eval_steps_per_second": 5.4,
|
| 437 |
+
"step": 282
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 29.74,
|
| 441 |
+
"learning_rate": 1.9753086419753087e-05,
|
| 442 |
+
"loss": 0.1192,
|
| 443 |
+
"step": 290
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 29.95,
|
| 447 |
+
"eval_accuracy": 0.9857142857142858,
|
| 448 |
+
"eval_loss": 0.02797979861497879,
|
| 449 |
+
"eval_runtime": 0.9576,
|
| 450 |
+
"eval_samples_per_second": 73.098,
|
| 451 |
+
"eval_steps_per_second": 5.221,
|
| 452 |
+
"step": 292
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 30.77,
|
| 456 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 457 |
+
"loss": 0.0896,
|
| 458 |
+
"step": 300
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 30.97,
|
| 462 |
+
"eval_accuracy": 0.9857142857142858,
|
| 463 |
+
"eval_loss": 0.03946752846240997,
|
| 464 |
+
"eval_runtime": 0.9155,
|
| 465 |
+
"eval_samples_per_second": 76.463,
|
| 466 |
+
"eval_steps_per_second": 5.462,
|
| 467 |
+
"step": 302
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 31.79,
|
| 471 |
+
"learning_rate": 1.728395061728395e-05,
|
| 472 |
+
"loss": 0.0778,
|
| 473 |
+
"step": 310
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 32.0,
|
| 477 |
+
"eval_accuracy": 1.0,
|
| 478 |
+
"eval_loss": 0.009111489169299603,
|
| 479 |
+
"eval_runtime": 0.9421,
|
| 480 |
+
"eval_samples_per_second": 74.306,
|
| 481 |
+
"eval_steps_per_second": 5.308,
|
| 482 |
+
"step": 312
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 32.82,
|
| 486 |
+
"learning_rate": 1.604938271604938e-05,
|
| 487 |
+
"loss": 0.0709,
|
| 488 |
+
"step": 320
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 32.92,
|
| 492 |
+
"eval_accuracy": 1.0,
|
| 493 |
+
"eval_loss": 0.006697469856590033,
|
| 494 |
+
"eval_runtime": 0.9422,
|
| 495 |
+
"eval_samples_per_second": 74.295,
|
| 496 |
+
"eval_steps_per_second": 5.307,
|
| 497 |
+
"step": 321
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 33.85,
|
| 501 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 502 |
+
"loss": 0.0603,
|
| 503 |
+
"step": 330
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 33.95,
|
| 507 |
+
"eval_accuracy": 1.0,
|
| 508 |
+
"eval_loss": 0.012383648194372654,
|
| 509 |
+
"eval_runtime": 0.9149,
|
| 510 |
+
"eval_samples_per_second": 76.511,
|
| 511 |
+
"eval_steps_per_second": 5.465,
|
| 512 |
+
"step": 331
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 34.87,
|
| 516 |
+
"learning_rate": 1.3580246913580247e-05,
|
| 517 |
+
"loss": 0.0777,
|
| 518 |
+
"step": 340
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 34.97,
|
| 522 |
+
"eval_accuracy": 0.9857142857142858,
|
| 523 |
+
"eval_loss": 0.035239022225141525,
|
| 524 |
+
"eval_runtime": 0.9299,
|
| 525 |
+
"eval_samples_per_second": 75.274,
|
| 526 |
+
"eval_steps_per_second": 5.377,
|
| 527 |
+
"step": 341
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 35.9,
|
| 531 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 532 |
+
"loss": 0.1045,
|
| 533 |
+
"step": 350
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 36.0,
|
| 537 |
+
"eval_accuracy": 1.0,
|
| 538 |
+
"eval_loss": 0.012970388866961002,
|
| 539 |
+
"eval_runtime": 0.9568,
|
| 540 |
+
"eval_samples_per_second": 73.163,
|
| 541 |
+
"eval_steps_per_second": 5.226,
|
| 542 |
+
"step": 351
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 36.92,
|
| 546 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 547 |
+
"loss": 0.0647,
|
| 548 |
+
"step": 360
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 36.92,
|
| 552 |
+
"eval_accuracy": 1.0,
|
| 553 |
+
"eval_loss": 0.0034227774012833834,
|
| 554 |
+
"eval_runtime": 0.9154,
|
| 555 |
+
"eval_samples_per_second": 76.471,
|
| 556 |
+
"eval_steps_per_second": 5.462,
|
| 557 |
+
"step": 360
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 37.95,
|
| 561 |
+
"learning_rate": 9.876543209876543e-06,
|
| 562 |
+
"loss": 0.0733,
|
| 563 |
+
"step": 370
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 37.95,
|
| 567 |
+
"eval_accuracy": 1.0,
|
| 568 |
+
"eval_loss": 0.005396140739321709,
|
| 569 |
+
"eval_runtime": 0.9146,
|
| 570 |
+
"eval_samples_per_second": 76.538,
|
| 571 |
+
"eval_steps_per_second": 5.467,
|
| 572 |
+
"step": 370
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 38.97,
|
| 576 |
+
"learning_rate": 8.641975308641975e-06,
|
| 577 |
+
"loss": 0.0576,
|
| 578 |
+
"step": 380
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 38.97,
|
| 582 |
+
"eval_accuracy": 0.9714285714285714,
|
| 583 |
+
"eval_loss": 0.024362746626138687,
|
| 584 |
+
"eval_runtime": 0.926,
|
| 585 |
+
"eval_samples_per_second": 75.596,
|
| 586 |
+
"eval_steps_per_second": 5.4,
|
| 587 |
+
"step": 380
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 40.0,
|
| 591 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 592 |
+
"loss": 0.0695,
|
| 593 |
+
"step": 390
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 40.0,
|
| 597 |
+
"eval_accuracy": 1.0,
|
| 598 |
+
"eval_loss": 0.002876411657780409,
|
| 599 |
+
"eval_runtime": 0.9256,
|
| 600 |
+
"eval_samples_per_second": 75.626,
|
| 601 |
+
"eval_steps_per_second": 5.402,
|
| 602 |
+
"step": 390
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 40.92,
|
| 606 |
+
"eval_accuracy": 1.0,
|
| 607 |
+
"eval_loss": 0.006180027965456247,
|
| 608 |
+
"eval_runtime": 0.916,
|
| 609 |
+
"eval_samples_per_second": 76.421,
|
| 610 |
+
"eval_steps_per_second": 5.459,
|
| 611 |
+
"step": 399
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 41.03,
|
| 615 |
+
"learning_rate": 6.172839506172839e-06,
|
| 616 |
+
"loss": 0.0592,
|
| 617 |
+
"step": 400
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 41.95,
|
| 621 |
+
"eval_accuracy": 1.0,
|
| 622 |
+
"eval_loss": 0.0032598855905234814,
|
| 623 |
+
"eval_runtime": 0.9432,
|
| 624 |
+
"eval_samples_per_second": 74.216,
|
| 625 |
+
"eval_steps_per_second": 5.301,
|
| 626 |
+
"step": 409
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 42.05,
|
| 630 |
+
"learning_rate": 4.938271604938272e-06,
|
| 631 |
+
"loss": 0.0643,
|
| 632 |
+
"step": 410
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 42.97,
|
| 636 |
+
"eval_accuracy": 1.0,
|
| 637 |
+
"eval_loss": 0.002199623268097639,
|
| 638 |
+
"eval_runtime": 0.9419,
|
| 639 |
+
"eval_samples_per_second": 74.319,
|
| 640 |
+
"eval_steps_per_second": 5.309,
|
| 641 |
+
"step": 419
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 43.08,
|
| 645 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 646 |
+
"loss": 0.0474,
|
| 647 |
+
"step": 420
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 44.0,
|
| 651 |
+
"eval_accuracy": 1.0,
|
| 652 |
+
"eval_loss": 0.0029794778674840927,
|
| 653 |
+
"eval_runtime": 0.9143,
|
| 654 |
+
"eval_samples_per_second": 76.558,
|
| 655 |
+
"eval_steps_per_second": 5.468,
|
| 656 |
+
"step": 429
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 44.1,
|
| 660 |
+
"learning_rate": 2.469135802469136e-06,
|
| 661 |
+
"loss": 0.085,
|
| 662 |
+
"step": 430
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 44.92,
|
| 666 |
+
"eval_accuracy": 1.0,
|
| 667 |
+
"eval_loss": 0.004402108024805784,
|
| 668 |
+
"eval_runtime": 0.926,
|
| 669 |
+
"eval_samples_per_second": 75.591,
|
| 670 |
+
"eval_steps_per_second": 5.399,
|
| 671 |
+
"step": 438
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 45.13,
|
| 675 |
+
"learning_rate": 1.234567901234568e-06,
|
| 676 |
+
"loss": 0.0472,
|
| 677 |
+
"step": 440
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 45.95,
|
| 681 |
+
"eval_accuracy": 1.0,
|
| 682 |
+
"eval_loss": 0.0060264961794018745,
|
| 683 |
+
"eval_runtime": 0.9252,
|
| 684 |
+
"eval_samples_per_second": 75.656,
|
| 685 |
+
"eval_steps_per_second": 5.404,
|
| 686 |
+
"step": 448
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 46.15,
|
| 690 |
+
"learning_rate": 0.0,
|
| 691 |
+
"loss": 0.0563,
|
| 692 |
+
"step": 450
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 46.15,
|
| 696 |
+
"eval_accuracy": 1.0,
|
| 697 |
+
"eval_loss": 0.006070576608181,
|
| 698 |
+
"eval_runtime": 0.9303,
|
| 699 |
+
"eval_samples_per_second": 75.246,
|
| 700 |
+
"eval_steps_per_second": 5.375,
|
| 701 |
+
"step": 450
|
| 702 |
+
}
|
| 703 |
+
],
|
| 704 |
+
"max_steps": 450,
|
| 705 |
+
"num_train_epochs": 50,
|
| 706 |
+
"total_flos": 2.437707333751603e+18,
|
| 707 |
+
"trial_name": null,
|
| 708 |
+
"trial_params": null
|
| 709 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56149ac38a9474bae86ee9ab78822516acc02cb214d57a3bbb4ac69dce4e3590
|
| 3 |
+
size 4027
|