Upload folder using huggingface_hub
Browse files- all_results.json +15 -0
- checkpoint-1750/config.json +83 -0
- checkpoint-1750/model.safetensors +3 -0
- checkpoint-1750/optimizer.pt +3 -0
- checkpoint-1750/preprocessor_config.json +22 -0
- checkpoint-1750/rng_state.pth +3 -0
- checkpoint-1750/scheduler.pt +3 -0
- checkpoint-1750/trainer_state.json +1407 -0
- checkpoint-1750/training_args.bin +3 -0
- config.json +83 -0
- eval_results.json +11 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- train_results.json +7 -0
- trainer_state.json +1506 -0
- training_args.bin +3 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.5952649379932357,
|
| 4 |
+
"eval_f1": 0.5714376467349129,
|
| 5 |
+
"eval_loss": 1.1634987592697144,
|
| 6 |
+
"eval_precision": 0.6038590156410394,
|
| 7 |
+
"eval_recall": 0.5952649379932357,
|
| 8 |
+
"eval_runtime": 21.9981,
|
| 9 |
+
"eval_samples_per_second": 80.643,
|
| 10 |
+
"eval_steps_per_second": 1.273,
|
| 11 |
+
"train_loss": 1.3704575569398942,
|
| 12 |
+
"train_runtime": 8385.7458,
|
| 13 |
+
"train_samples_per_second": 57.104,
|
| 14 |
+
"train_steps_per_second": 0.222
|
| 15 |
+
}
|
checkpoint-1750/config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Swinv2ForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"depths": [
|
| 8 |
+
2,
|
| 9 |
+
2,
|
| 10 |
+
18,
|
| 11 |
+
2
|
| 12 |
+
],
|
| 13 |
+
"drop_path_rate": 0.1,
|
| 14 |
+
"embed_dim": 192,
|
| 15 |
+
"encoder_stride": 32,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.0,
|
| 18 |
+
"hidden_size": 1536,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "Disturbed Galaxies",
|
| 21 |
+
"1": "Merging Galaxies",
|
| 22 |
+
"2": "Round Smooth Galaxies",
|
| 23 |
+
"3": "In-between Round Smooth Galaxies",
|
| 24 |
+
"4": "Cigar Shaped Smooth Galaxies",
|
| 25 |
+
"5": "Barred Spiral Galaxies",
|
| 26 |
+
"6": "Unbarred Tight Spiral Galaxies",
|
| 27 |
+
"7": "Unbarred Loose Spiral Galaxies",
|
| 28 |
+
"8": "Edge-on Galaxies without Bulge",
|
| 29 |
+
"9": "Edge-on Galaxies with Bulge"
|
| 30 |
+
},
|
| 31 |
+
"image_size": 256,
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"Barred Spiral Galaxies": 5,
|
| 35 |
+
"Cigar Shaped Smooth Galaxies": 4,
|
| 36 |
+
"Disturbed Galaxies": 0,
|
| 37 |
+
"Edge-on Galaxies with Bulge": 9,
|
| 38 |
+
"Edge-on Galaxies without Bulge": 8,
|
| 39 |
+
"In-between Round Smooth Galaxies": 3,
|
| 40 |
+
"Merging Galaxies": 1,
|
| 41 |
+
"Round Smooth Galaxies": 2,
|
| 42 |
+
"Unbarred Loose Spiral Galaxies": 7,
|
| 43 |
+
"Unbarred Tight Spiral Galaxies": 6
|
| 44 |
+
},
|
| 45 |
+
"layer_norm_eps": 1e-05,
|
| 46 |
+
"mlp_ratio": 4.0,
|
| 47 |
+
"model_type": "swinv2",
|
| 48 |
+
"num_channels": 3,
|
| 49 |
+
"num_heads": [
|
| 50 |
+
6,
|
| 51 |
+
12,
|
| 52 |
+
24,
|
| 53 |
+
48
|
| 54 |
+
],
|
| 55 |
+
"num_layers": 4,
|
| 56 |
+
"out_features": [
|
| 57 |
+
"stage4"
|
| 58 |
+
],
|
| 59 |
+
"out_indices": [
|
| 60 |
+
4
|
| 61 |
+
],
|
| 62 |
+
"patch_size": 4,
|
| 63 |
+
"path_norm": true,
|
| 64 |
+
"pretrained_window_sizes": [
|
| 65 |
+
12,
|
| 66 |
+
12,
|
| 67 |
+
12,
|
| 68 |
+
6
|
| 69 |
+
],
|
| 70 |
+
"problem_type": "single_label_classification",
|
| 71 |
+
"qkv_bias": true,
|
| 72 |
+
"stage_names": [
|
| 73 |
+
"stem",
|
| 74 |
+
"stage1",
|
| 75 |
+
"stage2",
|
| 76 |
+
"stage3",
|
| 77 |
+
"stage4"
|
| 78 |
+
],
|
| 79 |
+
"torch_dtype": "float32",
|
| 80 |
+
"transformers_version": "4.37.2",
|
| 81 |
+
"use_absolute_embeddings": false,
|
| 82 |
+
"window_size": 16
|
| 83 |
+
}
|
checkpoint-1750/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9df592770c26f76c77206bba25c3bd9e563d16dda5c26de88a6e023415e2ffc3
|
| 3 |
+
size 780935472
|
checkpoint-1750/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20e4f524750fdc479fb00efabae2ae7649341c8da230878d5e3c041375ad4d93
|
| 3 |
+
size 125724
|
checkpoint-1750/preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.485,
|
| 7 |
+
0.456,
|
| 8 |
+
0.406
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
],
|
| 16 |
+
"resample": 3,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 256,
|
| 20 |
+
"width": 256
|
| 21 |
+
}
|
| 22 |
+
}
|
checkpoint-1750/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ca82d479a5bc2e219b96b0e0f82ed5634d2bc0de921e8b673d7990a0aa6644f
|
| 3 |
+
size 14244
|
checkpoint-1750/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6beced7e8491b990d7f96a9cee50e6e798609de83f16e2dbc1991c31040c66ea
|
| 3 |
+
size 1064
|
checkpoint-1750/trainer_state.json
ADDED
|
@@ -0,0 +1,1407 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5952649379932357,
|
| 3 |
+
"best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-head-finetuned-galaxy10-decals/checkpoint-1750",
|
| 4 |
+
"epoch": 28.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1750,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"learning_rate": 5.376344086021506e-06,
|
| 14 |
+
"loss": 2.4183,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.32,
|
| 19 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 20 |
+
"loss": 2.3949,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.48,
|
| 25 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 26 |
+
"loss": 2.3777,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.64,
|
| 31 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 32 |
+
"loss": 2.335,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.8,
|
| 37 |
+
"learning_rate": 2.6881720430107527e-05,
|
| 38 |
+
"loss": 2.2929,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.96,
|
| 43 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 44 |
+
"loss": 2.2152,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.99,
|
| 49 |
+
"eval_accuracy": 0.20349492671927846,
|
| 50 |
+
"eval_f1": 0.15105203129445105,
|
| 51 |
+
"eval_loss": 2.188288927078247,
|
| 52 |
+
"eval_precision": 0.14895878509992708,
|
| 53 |
+
"eval_recall": 0.20349492671927846,
|
| 54 |
+
"eval_runtime": 22.1815,
|
| 55 |
+
"eval_samples_per_second": 79.976,
|
| 56 |
+
"eval_steps_per_second": 1.262,
|
| 57 |
+
"step": 62
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.12,
|
| 61 |
+
"learning_rate": 3.763440860215054e-05,
|
| 62 |
+
"loss": 2.1913,
|
| 63 |
+
"step": 70
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.28,
|
| 67 |
+
"learning_rate": 4.301075268817205e-05,
|
| 68 |
+
"loss": 2.1422,
|
| 69 |
+
"step": 80
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.44,
|
| 73 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 74 |
+
"loss": 2.0878,
|
| 75 |
+
"step": 90
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.6,
|
| 79 |
+
"learning_rate": 5.3763440860215054e-05,
|
| 80 |
+
"loss": 2.0411,
|
| 81 |
+
"step": 100
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.76,
|
| 85 |
+
"learning_rate": 5.913978494623657e-05,
|
| 86 |
+
"loss": 1.9976,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.92,
|
| 91 |
+
"learning_rate": 6.451612903225807e-05,
|
| 92 |
+
"loss": 1.9434,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.0,
|
| 97 |
+
"eval_accuracy": 0.3506200676437429,
|
| 98 |
+
"eval_f1": 0.272465935568218,
|
| 99 |
+
"eval_loss": 1.9051553010940552,
|
| 100 |
+
"eval_precision": 0.39556561793778316,
|
| 101 |
+
"eval_recall": 0.3506200676437429,
|
| 102 |
+
"eval_runtime": 22.0737,
|
| 103 |
+
"eval_samples_per_second": 80.367,
|
| 104 |
+
"eval_steps_per_second": 1.268,
|
| 105 |
+
"step": 125
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.08,
|
| 109 |
+
"learning_rate": 6.989247311827958e-05,
|
| 110 |
+
"loss": 1.8905,
|
| 111 |
+
"step": 130
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.24,
|
| 115 |
+
"learning_rate": 7.526881720430108e-05,
|
| 116 |
+
"loss": 1.8585,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.4,
|
| 121 |
+
"learning_rate": 8.064516129032258e-05,
|
| 122 |
+
"loss": 1.814,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.56,
|
| 127 |
+
"learning_rate": 8.60215053763441e-05,
|
| 128 |
+
"loss": 1.8007,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.72,
|
| 133 |
+
"learning_rate": 9.13978494623656e-05,
|
| 134 |
+
"loss": 1.7578,
|
| 135 |
+
"step": 170
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.88,
|
| 139 |
+
"learning_rate": 9.677419354838711e-05,
|
| 140 |
+
"loss": 1.7295,
|
| 141 |
+
"step": 180
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.99,
|
| 145 |
+
"eval_accuracy": 0.4368658399098083,
|
| 146 |
+
"eval_f1": 0.3915006667744191,
|
| 147 |
+
"eval_loss": 1.6789493560791016,
|
| 148 |
+
"eval_precision": 0.46298297663493393,
|
| 149 |
+
"eval_recall": 0.4368658399098083,
|
| 150 |
+
"eval_runtime": 22.0192,
|
| 151 |
+
"eval_samples_per_second": 80.566,
|
| 152 |
+
"eval_steps_per_second": 1.272,
|
| 153 |
+
"step": 187
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 3.04,
|
| 157 |
+
"learning_rate": 9.97610513739546e-05,
|
| 158 |
+
"loss": 1.7217,
|
| 159 |
+
"step": 190
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.2,
|
| 163 |
+
"learning_rate": 9.916367980884111e-05,
|
| 164 |
+
"loss": 1.6519,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.36,
|
| 169 |
+
"learning_rate": 9.85663082437276e-05,
|
| 170 |
+
"loss": 1.6417,
|
| 171 |
+
"step": 210
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.52,
|
| 175 |
+
"learning_rate": 9.79689366786141e-05,
|
| 176 |
+
"loss": 1.6192,
|
| 177 |
+
"step": 220
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.68,
|
| 181 |
+
"learning_rate": 9.73715651135006e-05,
|
| 182 |
+
"loss": 1.6046,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.84,
|
| 187 |
+
"learning_rate": 9.677419354838711e-05,
|
| 188 |
+
"loss": 1.5931,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.0,
|
| 193 |
+
"learning_rate": 9.61768219832736e-05,
|
| 194 |
+
"loss": 1.5541,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.0,
|
| 199 |
+
"eval_accuracy": 0.47576099210823,
|
| 200 |
+
"eval_f1": 0.4335867277644615,
|
| 201 |
+
"eval_loss": 1.5338377952575684,
|
| 202 |
+
"eval_precision": 0.509541084219624,
|
| 203 |
+
"eval_recall": 0.47576099210823,
|
| 204 |
+
"eval_runtime": 22.1469,
|
| 205 |
+
"eval_samples_per_second": 80.102,
|
| 206 |
+
"eval_steps_per_second": 1.264,
|
| 207 |
+
"step": 250
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.16,
|
| 211 |
+
"learning_rate": 9.55794504181601e-05,
|
| 212 |
+
"loss": 1.5557,
|
| 213 |
+
"step": 260
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.32,
|
| 217 |
+
"learning_rate": 9.49820788530466e-05,
|
| 218 |
+
"loss": 1.5259,
|
| 219 |
+
"step": 270
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.48,
|
| 223 |
+
"learning_rate": 9.438470728793309e-05,
|
| 224 |
+
"loss": 1.5044,
|
| 225 |
+
"step": 280
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.64,
|
| 229 |
+
"learning_rate": 9.378733572281961e-05,
|
| 230 |
+
"loss": 1.5017,
|
| 231 |
+
"step": 290
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 4.8,
|
| 235 |
+
"learning_rate": 9.31899641577061e-05,
|
| 236 |
+
"loss": 1.4979,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.96,
|
| 241 |
+
"learning_rate": 9.25925925925926e-05,
|
| 242 |
+
"loss": 1.4558,
|
| 243 |
+
"step": 310
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 4.99,
|
| 247 |
+
"eval_accuracy": 0.520293122886133,
|
| 248 |
+
"eval_f1": 0.48596376905849764,
|
| 249 |
+
"eval_loss": 1.4501919746398926,
|
| 250 |
+
"eval_precision": 0.5414266437447433,
|
| 251 |
+
"eval_recall": 0.520293122886133,
|
| 252 |
+
"eval_runtime": 22.0839,
|
| 253 |
+
"eval_samples_per_second": 80.33,
|
| 254 |
+
"eval_steps_per_second": 1.268,
|
| 255 |
+
"step": 312
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 5.12,
|
| 259 |
+
"learning_rate": 9.199522102747909e-05,
|
| 260 |
+
"loss": 1.4861,
|
| 261 |
+
"step": 320
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.28,
|
| 265 |
+
"learning_rate": 9.13978494623656e-05,
|
| 266 |
+
"loss": 1.4779,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 5.44,
|
| 271 |
+
"learning_rate": 9.080047789725208e-05,
|
| 272 |
+
"loss": 1.4526,
|
| 273 |
+
"step": 340
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 5.6,
|
| 277 |
+
"learning_rate": 9.02031063321386e-05,
|
| 278 |
+
"loss": 1.4667,
|
| 279 |
+
"step": 350
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 5.76,
|
| 283 |
+
"learning_rate": 8.960573476702509e-05,
|
| 284 |
+
"loss": 1.4395,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 5.92,
|
| 289 |
+
"learning_rate": 8.900836320191159e-05,
|
| 290 |
+
"loss": 1.42,
|
| 291 |
+
"step": 370
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 6.0,
|
| 295 |
+
"eval_accuracy": 0.520293122886133,
|
| 296 |
+
"eval_f1": 0.4892009598786175,
|
| 297 |
+
"eval_loss": 1.399051308631897,
|
| 298 |
+
"eval_precision": 0.5529206104546609,
|
| 299 |
+
"eval_recall": 0.520293122886133,
|
| 300 |
+
"eval_runtime": 22.0309,
|
| 301 |
+
"eval_samples_per_second": 80.523,
|
| 302 |
+
"eval_steps_per_second": 1.271,
|
| 303 |
+
"step": 375
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.08,
|
| 307 |
+
"learning_rate": 8.84109916367981e-05,
|
| 308 |
+
"loss": 1.4285,
|
| 309 |
+
"step": 380
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.24,
|
| 313 |
+
"learning_rate": 8.781362007168459e-05,
|
| 314 |
+
"loss": 1.4283,
|
| 315 |
+
"step": 390
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.4,
|
| 319 |
+
"learning_rate": 8.72162485065711e-05,
|
| 320 |
+
"loss": 1.3969,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 6.56,
|
| 325 |
+
"learning_rate": 8.661887694145759e-05,
|
| 326 |
+
"loss": 1.4135,
|
| 327 |
+
"step": 410
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.72,
|
| 331 |
+
"learning_rate": 8.60215053763441e-05,
|
| 332 |
+
"loss": 1.3878,
|
| 333 |
+
"step": 420
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 6.88,
|
| 337 |
+
"learning_rate": 8.542413381123058e-05,
|
| 338 |
+
"loss": 1.3806,
|
| 339 |
+
"step": 430
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.99,
|
| 343 |
+
"eval_accuracy": 0.5501691093573844,
|
| 344 |
+
"eval_f1": 0.5227011346941011,
|
| 345 |
+
"eval_loss": 1.3529337644577026,
|
| 346 |
+
"eval_precision": 0.5732264535553914,
|
| 347 |
+
"eval_recall": 0.5501691093573844,
|
| 348 |
+
"eval_runtime": 22.1773,
|
| 349 |
+
"eval_samples_per_second": 79.992,
|
| 350 |
+
"eval_steps_per_second": 1.263,
|
| 351 |
+
"step": 437
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 7.04,
|
| 355 |
+
"learning_rate": 8.482676224611709e-05,
|
| 356 |
+
"loss": 1.4184,
|
| 357 |
+
"step": 440
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 7.2,
|
| 361 |
+
"learning_rate": 8.422939068100359e-05,
|
| 362 |
+
"loss": 1.4169,
|
| 363 |
+
"step": 450
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 7.36,
|
| 367 |
+
"learning_rate": 8.363201911589009e-05,
|
| 368 |
+
"loss": 1.3882,
|
| 369 |
+
"step": 460
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 7.52,
|
| 373 |
+
"learning_rate": 8.30346475507766e-05,
|
| 374 |
+
"loss": 1.3869,
|
| 375 |
+
"step": 470
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 7.68,
|
| 379 |
+
"learning_rate": 8.243727598566309e-05,
|
| 380 |
+
"loss": 1.3499,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 7.84,
|
| 385 |
+
"learning_rate": 8.183990442054959e-05,
|
| 386 |
+
"loss": 1.3531,
|
| 387 |
+
"step": 490
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.0,
|
| 391 |
+
"learning_rate": 8.124253285543608e-05,
|
| 392 |
+
"loss": 1.3541,
|
| 393 |
+
"step": 500
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 8.0,
|
| 397 |
+
"eval_accuracy": 0.560315670800451,
|
| 398 |
+
"eval_f1": 0.532522788067071,
|
| 399 |
+
"eval_loss": 1.3217679262161255,
|
| 400 |
+
"eval_precision": 0.5934036230328783,
|
| 401 |
+
"eval_recall": 0.560315670800451,
|
| 402 |
+
"eval_runtime": 22.0874,
|
| 403 |
+
"eval_samples_per_second": 80.317,
|
| 404 |
+
"eval_steps_per_second": 1.268,
|
| 405 |
+
"step": 500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 8.16,
|
| 409 |
+
"learning_rate": 8.064516129032258e-05,
|
| 410 |
+
"loss": 1.3568,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 8.32,
|
| 415 |
+
"learning_rate": 8.004778972520908e-05,
|
| 416 |
+
"loss": 1.3505,
|
| 417 |
+
"step": 520
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.48,
|
| 421 |
+
"learning_rate": 7.945041816009559e-05,
|
| 422 |
+
"loss": 1.397,
|
| 423 |
+
"step": 530
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 8.64,
|
| 427 |
+
"learning_rate": 7.885304659498209e-05,
|
| 428 |
+
"loss": 1.3614,
|
| 429 |
+
"step": 540
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 8.8,
|
| 433 |
+
"learning_rate": 7.825567502986858e-05,
|
| 434 |
+
"loss": 1.3543,
|
| 435 |
+
"step": 550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 8.96,
|
| 439 |
+
"learning_rate": 7.765830346475508e-05,
|
| 440 |
+
"loss": 1.337,
|
| 441 |
+
"step": 560
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 8.99,
|
| 445 |
+
"eval_accuracy": 0.5597519729425028,
|
| 446 |
+
"eval_f1": 0.5304260590298405,
|
| 447 |
+
"eval_loss": 1.3014049530029297,
|
| 448 |
+
"eval_precision": 0.6007885455628412,
|
| 449 |
+
"eval_recall": 0.5597519729425028,
|
| 450 |
+
"eval_runtime": 22.0361,
|
| 451 |
+
"eval_samples_per_second": 80.504,
|
| 452 |
+
"eval_steps_per_second": 1.271,
|
| 453 |
+
"step": 562
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 9.12,
|
| 457 |
+
"learning_rate": 7.706093189964157e-05,
|
| 458 |
+
"loss": 1.359,
|
| 459 |
+
"step": 570
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 9.28,
|
| 463 |
+
"learning_rate": 7.646356033452809e-05,
|
| 464 |
+
"loss": 1.3222,
|
| 465 |
+
"step": 580
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 9.44,
|
| 469 |
+
"learning_rate": 7.586618876941458e-05,
|
| 470 |
+
"loss": 1.3325,
|
| 471 |
+
"step": 590
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 9.6,
|
| 475 |
+
"learning_rate": 7.526881720430108e-05,
|
| 476 |
+
"loss": 1.3524,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 9.76,
|
| 481 |
+
"learning_rate": 7.467144563918757e-05,
|
| 482 |
+
"loss": 1.3077,
|
| 483 |
+
"step": 610
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 9.92,
|
| 487 |
+
"learning_rate": 7.407407407407407e-05,
|
| 488 |
+
"loss": 1.3164,
|
| 489 |
+
"step": 620
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 10.0,
|
| 493 |
+
"eval_accuracy": 0.5552423900789177,
|
| 494 |
+
"eval_f1": 0.5269514020319623,
|
| 495 |
+
"eval_loss": 1.285463571548462,
|
| 496 |
+
"eval_precision": 0.5617951310681798,
|
| 497 |
+
"eval_recall": 0.5552423900789177,
|
| 498 |
+
"eval_runtime": 22.0709,
|
| 499 |
+
"eval_samples_per_second": 80.377,
|
| 500 |
+
"eval_steps_per_second": 1.269,
|
| 501 |
+
"step": 625
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 10.08,
|
| 505 |
+
"learning_rate": 7.347670250896058e-05,
|
| 506 |
+
"loss": 1.336,
|
| 507 |
+
"step": 630
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 10.24,
|
| 511 |
+
"learning_rate": 7.287933094384708e-05,
|
| 512 |
+
"loss": 1.3231,
|
| 513 |
+
"step": 640
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 10.4,
|
| 517 |
+
"learning_rate": 7.228195937873358e-05,
|
| 518 |
+
"loss": 1.3111,
|
| 519 |
+
"step": 650
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 10.56,
|
| 523 |
+
"learning_rate": 7.168458781362007e-05,
|
| 524 |
+
"loss": 1.3081,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 10.72,
|
| 529 |
+
"learning_rate": 7.108721624850657e-05,
|
| 530 |
+
"loss": 1.2971,
|
| 531 |
+
"step": 670
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 10.88,
|
| 535 |
+
"learning_rate": 7.048984468339306e-05,
|
| 536 |
+
"loss": 1.2904,
|
| 537 |
+
"step": 680
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 10.99,
|
| 541 |
+
"eval_accuracy": 0.5715896279594137,
|
| 542 |
+
"eval_f1": 0.544321340926892,
|
| 543 |
+
"eval_loss": 1.2624871730804443,
|
| 544 |
+
"eval_precision": 0.6199672961362004,
|
| 545 |
+
"eval_recall": 0.5715896279594137,
|
| 546 |
+
"eval_runtime": 22.0129,
|
| 547 |
+
"eval_samples_per_second": 80.589,
|
| 548 |
+
"eval_steps_per_second": 1.272,
|
| 549 |
+
"step": 687
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 11.04,
|
| 553 |
+
"learning_rate": 6.989247311827958e-05,
|
| 554 |
+
"loss": 1.3266,
|
| 555 |
+
"step": 690
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 11.2,
|
| 559 |
+
"learning_rate": 6.929510155316607e-05,
|
| 560 |
+
"loss": 1.3018,
|
| 561 |
+
"step": 700
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 11.36,
|
| 565 |
+
"learning_rate": 6.869772998805257e-05,
|
| 566 |
+
"loss": 1.2864,
|
| 567 |
+
"step": 710
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 11.52,
|
| 571 |
+
"learning_rate": 6.810035842293908e-05,
|
| 572 |
+
"loss": 1.3119,
|
| 573 |
+
"step": 720
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 11.68,
|
| 577 |
+
"learning_rate": 6.750298685782557e-05,
|
| 578 |
+
"loss": 1.2891,
|
| 579 |
+
"step": 730
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 11.84,
|
| 583 |
+
"learning_rate": 6.690561529271207e-05,
|
| 584 |
+
"loss": 1.2815,
|
| 585 |
+
"step": 740
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 12.0,
|
| 589 |
+
"learning_rate": 6.630824372759857e-05,
|
| 590 |
+
"loss": 1.2873,
|
| 591 |
+
"step": 750
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 12.0,
|
| 595 |
+
"eval_accuracy": 0.5698985343855694,
|
| 596 |
+
"eval_f1": 0.5446306363255216,
|
| 597 |
+
"eval_loss": 1.248738169670105,
|
| 598 |
+
"eval_precision": 0.5943470885639225,
|
| 599 |
+
"eval_recall": 0.5698985343855694,
|
| 600 |
+
"eval_runtime": 21.9956,
|
| 601 |
+
"eval_samples_per_second": 80.653,
|
| 602 |
+
"eval_steps_per_second": 1.273,
|
| 603 |
+
"step": 750
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 12.16,
|
| 607 |
+
"learning_rate": 6.571087216248507e-05,
|
| 608 |
+
"loss": 1.2642,
|
| 609 |
+
"step": 760
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 12.32,
|
| 613 |
+
"learning_rate": 6.511350059737156e-05,
|
| 614 |
+
"loss": 1.2815,
|
| 615 |
+
"step": 770
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 12.48,
|
| 619 |
+
"learning_rate": 6.451612903225807e-05,
|
| 620 |
+
"loss": 1.2987,
|
| 621 |
+
"step": 780
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 12.64,
|
| 625 |
+
"learning_rate": 6.391875746714456e-05,
|
| 626 |
+
"loss": 1.2964,
|
| 627 |
+
"step": 790
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 12.8,
|
| 631 |
+
"learning_rate": 6.332138590203107e-05,
|
| 632 |
+
"loss": 1.2946,
|
| 633 |
+
"step": 800
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 12.96,
|
| 637 |
+
"learning_rate": 6.272401433691756e-05,
|
| 638 |
+
"loss": 1.2911,
|
| 639 |
+
"step": 810
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 12.99,
|
| 643 |
+
"eval_accuracy": 0.5772266065388951,
|
| 644 |
+
"eval_f1": 0.5531271982911073,
|
| 645 |
+
"eval_loss": 1.2366129159927368,
|
| 646 |
+
"eval_precision": 0.6023489690717835,
|
| 647 |
+
"eval_recall": 0.5772266065388951,
|
| 648 |
+
"eval_runtime": 22.1699,
|
| 649 |
+
"eval_samples_per_second": 80.019,
|
| 650 |
+
"eval_steps_per_second": 1.263,
|
| 651 |
+
"step": 812
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 13.12,
|
| 655 |
+
"learning_rate": 6.212664277180407e-05,
|
| 656 |
+
"loss": 1.2581,
|
| 657 |
+
"step": 820
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 13.28,
|
| 661 |
+
"learning_rate": 6.152927120669057e-05,
|
| 662 |
+
"loss": 1.2737,
|
| 663 |
+
"step": 830
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 13.44,
|
| 667 |
+
"learning_rate": 6.093189964157706e-05,
|
| 668 |
+
"loss": 1.2834,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 13.6,
|
| 673 |
+
"learning_rate": 6.033452807646356e-05,
|
| 674 |
+
"loss": 1.2522,
|
| 675 |
+
"step": 850
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 13.76,
|
| 679 |
+
"learning_rate": 5.9737156511350064e-05,
|
| 680 |
+
"loss": 1.2698,
|
| 681 |
+
"step": 860
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 13.92,
|
| 685 |
+
"learning_rate": 5.913978494623657e-05,
|
| 686 |
+
"loss": 1.2723,
|
| 687 |
+
"step": 870
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 14.0,
|
| 691 |
+
"eval_accuracy": 0.5817361894024803,
|
| 692 |
+
"eval_f1": 0.55938608951765,
|
| 693 |
+
"eval_loss": 1.2241930961608887,
|
| 694 |
+
"eval_precision": 0.5945742291844911,
|
| 695 |
+
"eval_recall": 0.5817361894024803,
|
| 696 |
+
"eval_runtime": 21.9188,
|
| 697 |
+
"eval_samples_per_second": 80.935,
|
| 698 |
+
"eval_steps_per_second": 1.277,
|
| 699 |
+
"step": 875
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 14.08,
|
| 703 |
+
"learning_rate": 5.8542413381123063e-05,
|
| 704 |
+
"loss": 1.2748,
|
| 705 |
+
"step": 880
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 14.24,
|
| 709 |
+
"learning_rate": 5.794504181600956e-05,
|
| 710 |
+
"loss": 1.2495,
|
| 711 |
+
"step": 890
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 14.4,
|
| 715 |
+
"learning_rate": 5.7347670250896056e-05,
|
| 716 |
+
"loss": 1.2677,
|
| 717 |
+
"step": 900
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 14.56,
|
| 721 |
+
"learning_rate": 5.675029868578255e-05,
|
| 722 |
+
"loss": 1.265,
|
| 723 |
+
"step": 910
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 14.72,
|
| 727 |
+
"learning_rate": 5.615292712066906e-05,
|
| 728 |
+
"loss": 1.2726,
|
| 729 |
+
"step": 920
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 14.88,
|
| 733 |
+
"learning_rate": 5.555555555555556e-05,
|
| 734 |
+
"loss": 1.2527,
|
| 735 |
+
"step": 930
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 14.99,
|
| 739 |
+
"eval_accuracy": 0.5822998872604284,
|
| 740 |
+
"eval_f1": 0.5601846765224702,
|
| 741 |
+
"eval_loss": 1.2167905569076538,
|
| 742 |
+
"eval_precision": 0.5957646682172907,
|
| 743 |
+
"eval_recall": 0.5822998872604284,
|
| 744 |
+
"eval_runtime": 22.0356,
|
| 745 |
+
"eval_samples_per_second": 80.506,
|
| 746 |
+
"eval_steps_per_second": 1.271,
|
| 747 |
+
"step": 937
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 15.04,
|
| 751 |
+
"learning_rate": 5.495818399044206e-05,
|
| 752 |
+
"loss": 1.2631,
|
| 753 |
+
"step": 940
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 15.2,
|
| 757 |
+
"learning_rate": 5.436081242532856e-05,
|
| 758 |
+
"loss": 1.2596,
|
| 759 |
+
"step": 950
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 15.36,
|
| 763 |
+
"learning_rate": 5.3763440860215054e-05,
|
| 764 |
+
"loss": 1.257,
|
| 765 |
+
"step": 960
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 15.52,
|
| 769 |
+
"learning_rate": 5.316606929510155e-05,
|
| 770 |
+
"loss": 1.2618,
|
| 771 |
+
"step": 970
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 15.68,
|
| 775 |
+
"learning_rate": 5.256869772998806e-05,
|
| 776 |
+
"loss": 1.2497,
|
| 777 |
+
"step": 980
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 15.84,
|
| 781 |
+
"learning_rate": 5.1971326164874556e-05,
|
| 782 |
+
"loss": 1.2499,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 16.0,
|
| 787 |
+
"learning_rate": 5.137395459976105e-05,
|
| 788 |
+
"loss": 1.2692,
|
| 789 |
+
"step": 1000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 16.0,
|
| 793 |
+
"eval_accuracy": 0.5856820744081173,
|
| 794 |
+
"eval_f1": 0.5625146496179491,
|
| 795 |
+
"eval_loss": 1.2087658643722534,
|
| 796 |
+
"eval_precision": 0.6014714549054646,
|
| 797 |
+
"eval_recall": 0.5856820744081173,
|
| 798 |
+
"eval_runtime": 22.0433,
|
| 799 |
+
"eval_samples_per_second": 80.478,
|
| 800 |
+
"eval_steps_per_second": 1.27,
|
| 801 |
+
"step": 1000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 16.16,
|
| 805 |
+
"learning_rate": 5.077658303464755e-05,
|
| 806 |
+
"loss": 1.2429,
|
| 807 |
+
"step": 1010
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 16.32,
|
| 811 |
+
"learning_rate": 5.017921146953405e-05,
|
| 812 |
+
"loss": 1.2498,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 16.48,
|
| 817 |
+
"learning_rate": 4.9581839904420555e-05,
|
| 818 |
+
"loss": 1.2689,
|
| 819 |
+
"step": 1030
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 16.64,
|
| 823 |
+
"learning_rate": 4.898446833930705e-05,
|
| 824 |
+
"loss": 1.2683,
|
| 825 |
+
"step": 1040
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 16.8,
|
| 829 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 830 |
+
"loss": 1.2617,
|
| 831 |
+
"step": 1050
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 16.96,
|
| 835 |
+
"learning_rate": 4.778972520908005e-05,
|
| 836 |
+
"loss": 1.2279,
|
| 837 |
+
"step": 1060
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 16.99,
|
| 841 |
+
"eval_accuracy": 0.5851183765501691,
|
| 842 |
+
"eval_f1": 0.5622039743774847,
|
| 843 |
+
"eval_loss": 1.203583836555481,
|
| 844 |
+
"eval_precision": 0.60014103604046,
|
| 845 |
+
"eval_recall": 0.5851183765501691,
|
| 846 |
+
"eval_runtime": 22.1622,
|
| 847 |
+
"eval_samples_per_second": 80.046,
|
| 848 |
+
"eval_steps_per_second": 1.263,
|
| 849 |
+
"step": 1062
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 17.12,
|
| 853 |
+
"learning_rate": 4.7192353643966546e-05,
|
| 854 |
+
"loss": 1.217,
|
| 855 |
+
"step": 1070
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 17.28,
|
| 859 |
+
"learning_rate": 4.659498207885305e-05,
|
| 860 |
+
"loss": 1.2531,
|
| 861 |
+
"step": 1080
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 17.44,
|
| 865 |
+
"learning_rate": 4.5997610513739546e-05,
|
| 866 |
+
"loss": 1.2634,
|
| 867 |
+
"step": 1090
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 17.6,
|
| 871 |
+
"learning_rate": 4.540023894862604e-05,
|
| 872 |
+
"loss": 1.2465,
|
| 873 |
+
"step": 1100
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 17.76,
|
| 877 |
+
"learning_rate": 4.4802867383512545e-05,
|
| 878 |
+
"loss": 1.2665,
|
| 879 |
+
"step": 1110
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 17.92,
|
| 883 |
+
"learning_rate": 4.420549581839905e-05,
|
| 884 |
+
"loss": 1.2539,
|
| 885 |
+
"step": 1120
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 18.0,
|
| 889 |
+
"eval_accuracy": 0.5822998872604284,
|
| 890 |
+
"eval_f1": 0.5591138810402552,
|
| 891 |
+
"eval_loss": 1.1966551542282104,
|
| 892 |
+
"eval_precision": 0.6010933850255593,
|
| 893 |
+
"eval_recall": 0.5822998872604284,
|
| 894 |
+
"eval_runtime": 22.0507,
|
| 895 |
+
"eval_samples_per_second": 80.451,
|
| 896 |
+
"eval_steps_per_second": 1.27,
|
| 897 |
+
"step": 1125
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 18.08,
|
| 901 |
+
"learning_rate": 4.360812425328555e-05,
|
| 902 |
+
"loss": 1.2355,
|
| 903 |
+
"step": 1130
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 18.24,
|
| 907 |
+
"learning_rate": 4.301075268817205e-05,
|
| 908 |
+
"loss": 1.2481,
|
| 909 |
+
"step": 1140
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 18.4,
|
| 913 |
+
"learning_rate": 4.241338112305854e-05,
|
| 914 |
+
"loss": 1.2128,
|
| 915 |
+
"step": 1150
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 18.56,
|
| 919 |
+
"learning_rate": 4.1816009557945046e-05,
|
| 920 |
+
"loss": 1.2455,
|
| 921 |
+
"step": 1160
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 18.72,
|
| 925 |
+
"learning_rate": 4.121863799283154e-05,
|
| 926 |
+
"loss": 1.2491,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 18.88,
|
| 931 |
+
"learning_rate": 4.062126642771804e-05,
|
| 932 |
+
"loss": 1.2341,
|
| 933 |
+
"step": 1180
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 18.99,
|
| 937 |
+
"eval_accuracy": 0.5907553551296505,
|
| 938 |
+
"eval_f1": 0.5665315520801317,
|
| 939 |
+
"eval_loss": 1.187435269355774,
|
| 940 |
+
"eval_precision": 0.6124355427768795,
|
| 941 |
+
"eval_recall": 0.5907553551296505,
|
| 942 |
+
"eval_runtime": 22.0769,
|
| 943 |
+
"eval_samples_per_second": 80.356,
|
| 944 |
+
"eval_steps_per_second": 1.268,
|
| 945 |
+
"step": 1187
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 19.04,
|
| 949 |
+
"learning_rate": 4.002389486260454e-05,
|
| 950 |
+
"loss": 1.2278,
|
| 951 |
+
"step": 1190
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 19.2,
|
| 955 |
+
"learning_rate": 3.9426523297491045e-05,
|
| 956 |
+
"loss": 1.2442,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 19.36,
|
| 961 |
+
"learning_rate": 3.882915173237754e-05,
|
| 962 |
+
"loss": 1.2192,
|
| 963 |
+
"step": 1210
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 19.52,
|
| 967 |
+
"learning_rate": 3.8231780167264044e-05,
|
| 968 |
+
"loss": 1.2532,
|
| 969 |
+
"step": 1220
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 19.68,
|
| 973 |
+
"learning_rate": 3.763440860215054e-05,
|
| 974 |
+
"loss": 1.2309,
|
| 975 |
+
"step": 1230
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 19.84,
|
| 979 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 980 |
+
"loss": 1.2555,
|
| 981 |
+
"step": 1240
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 20.0,
|
| 985 |
+
"learning_rate": 3.643966547192354e-05,
|
| 986 |
+
"loss": 1.2475,
|
| 987 |
+
"step": 1250
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 20.0,
|
| 991 |
+
"eval_accuracy": 0.584554678692221,
|
| 992 |
+
"eval_f1": 0.5598437529375522,
|
| 993 |
+
"eval_loss": 1.1870439052581787,
|
| 994 |
+
"eval_precision": 0.6019233382358613,
|
| 995 |
+
"eval_recall": 0.584554678692221,
|
| 996 |
+
"eval_runtime": 21.6957,
|
| 997 |
+
"eval_samples_per_second": 81.767,
|
| 998 |
+
"eval_steps_per_second": 1.291,
|
| 999 |
+
"step": 1250
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 20.16,
|
| 1003 |
+
"learning_rate": 3.5842293906810036e-05,
|
| 1004 |
+
"loss": 1.2521,
|
| 1005 |
+
"step": 1260
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 20.32,
|
| 1009 |
+
"learning_rate": 3.524492234169653e-05,
|
| 1010 |
+
"loss": 1.2373,
|
| 1011 |
+
"step": 1270
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 20.48,
|
| 1015 |
+
"learning_rate": 3.4647550776583035e-05,
|
| 1016 |
+
"loss": 1.2188,
|
| 1017 |
+
"step": 1280
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 20.64,
|
| 1021 |
+
"learning_rate": 3.405017921146954e-05,
|
| 1022 |
+
"loss": 1.2398,
|
| 1023 |
+
"step": 1290
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 20.8,
|
| 1027 |
+
"learning_rate": 3.3452807646356034e-05,
|
| 1028 |
+
"loss": 1.2405,
|
| 1029 |
+
"step": 1300
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 20.96,
|
| 1033 |
+
"learning_rate": 3.285543608124254e-05,
|
| 1034 |
+
"loss": 1.2009,
|
| 1035 |
+
"step": 1310
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 20.99,
|
| 1039 |
+
"eval_accuracy": 0.593010146561443,
|
| 1040 |
+
"eval_f1": 0.5691157408882564,
|
| 1041 |
+
"eval_loss": 1.1792354583740234,
|
| 1042 |
+
"eval_precision": 0.6069905496006659,
|
| 1043 |
+
"eval_recall": 0.593010146561443,
|
| 1044 |
+
"eval_runtime": 21.918,
|
| 1045 |
+
"eval_samples_per_second": 80.938,
|
| 1046 |
+
"eval_steps_per_second": 1.277,
|
| 1047 |
+
"step": 1312
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 21.12,
|
| 1051 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 1052 |
+
"loss": 1.2068,
|
| 1053 |
+
"step": 1320
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 21.28,
|
| 1057 |
+
"learning_rate": 3.1660692951015537e-05,
|
| 1058 |
+
"loss": 1.2272,
|
| 1059 |
+
"step": 1330
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 21.44,
|
| 1063 |
+
"learning_rate": 3.106332138590203e-05,
|
| 1064 |
+
"loss": 1.2156,
|
| 1065 |
+
"step": 1340
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 21.6,
|
| 1069 |
+
"learning_rate": 3.046594982078853e-05,
|
| 1070 |
+
"loss": 1.2154,
|
| 1071 |
+
"step": 1350
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 21.76,
|
| 1075 |
+
"learning_rate": 2.9868578255675032e-05,
|
| 1076 |
+
"loss": 1.214,
|
| 1077 |
+
"step": 1360
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 21.92,
|
| 1081 |
+
"learning_rate": 2.9271206690561532e-05,
|
| 1082 |
+
"loss": 1.2515,
|
| 1083 |
+
"step": 1370
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 22.0,
|
| 1087 |
+
"eval_accuracy": 0.5918827508455468,
|
| 1088 |
+
"eval_f1": 0.5678475976802037,
|
| 1089 |
+
"eval_loss": 1.1771893501281738,
|
| 1090 |
+
"eval_precision": 0.606224629917707,
|
| 1091 |
+
"eval_recall": 0.5918827508455468,
|
| 1092 |
+
"eval_runtime": 21.8417,
|
| 1093 |
+
"eval_samples_per_second": 81.221,
|
| 1094 |
+
"eval_steps_per_second": 1.282,
|
| 1095 |
+
"step": 1375
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 22.08,
|
| 1099 |
+
"learning_rate": 2.8673835125448028e-05,
|
| 1100 |
+
"loss": 1.2501,
|
| 1101 |
+
"step": 1380
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 22.24,
|
| 1105 |
+
"learning_rate": 2.807646356033453e-05,
|
| 1106 |
+
"loss": 1.2147,
|
| 1107 |
+
"step": 1390
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 22.4,
|
| 1111 |
+
"learning_rate": 2.747909199522103e-05,
|
| 1112 |
+
"loss": 1.184,
|
| 1113 |
+
"step": 1400
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 22.56,
|
| 1117 |
+
"learning_rate": 2.6881720430107527e-05,
|
| 1118 |
+
"loss": 1.2386,
|
| 1119 |
+
"step": 1410
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 22.72,
|
| 1123 |
+
"learning_rate": 2.628434886499403e-05,
|
| 1124 |
+
"loss": 1.2336,
|
| 1125 |
+
"step": 1420
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 22.88,
|
| 1129 |
+
"learning_rate": 2.5686977299880526e-05,
|
| 1130 |
+
"loss": 1.2361,
|
| 1131 |
+
"step": 1430
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 22.99,
|
| 1135 |
+
"eval_accuracy": 0.5918827508455468,
|
| 1136 |
+
"eval_f1": 0.5680339449025893,
|
| 1137 |
+
"eval_loss": 1.1749292612075806,
|
| 1138 |
+
"eval_precision": 0.6079590653989706,
|
| 1139 |
+
"eval_recall": 0.5918827508455468,
|
| 1140 |
+
"eval_runtime": 21.9917,
|
| 1141 |
+
"eval_samples_per_second": 80.667,
|
| 1142 |
+
"eval_steps_per_second": 1.273,
|
| 1143 |
+
"step": 1437
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 23.04,
|
| 1147 |
+
"learning_rate": 2.5089605734767026e-05,
|
| 1148 |
+
"loss": 1.2493,
|
| 1149 |
+
"step": 1440
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 23.2,
|
| 1153 |
+
"learning_rate": 2.4492234169653525e-05,
|
| 1154 |
+
"loss": 1.2109,
|
| 1155 |
+
"step": 1450
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 23.36,
|
| 1159 |
+
"learning_rate": 2.3894862604540025e-05,
|
| 1160 |
+
"loss": 1.2227,
|
| 1161 |
+
"step": 1460
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 23.52,
|
| 1165 |
+
"learning_rate": 2.3297491039426525e-05,
|
| 1166 |
+
"loss": 1.2163,
|
| 1167 |
+
"step": 1470
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 23.68,
|
| 1171 |
+
"learning_rate": 2.270011947431302e-05,
|
| 1172 |
+
"loss": 1.2372,
|
| 1173 |
+
"step": 1480
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 23.84,
|
| 1177 |
+
"learning_rate": 2.2102747909199524e-05,
|
| 1178 |
+
"loss": 1.1965,
|
| 1179 |
+
"step": 1490
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 24.0,
|
| 1183 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 1184 |
+
"loss": 1.2366,
|
| 1185 |
+
"step": 1500
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 24.0,
|
| 1189 |
+
"eval_accuracy": 0.5924464487034949,
|
| 1190 |
+
"eval_f1": 0.5690711817132577,
|
| 1191 |
+
"eval_loss": 1.1708468198776245,
|
| 1192 |
+
"eval_precision": 0.6047825042790245,
|
| 1193 |
+
"eval_recall": 0.5924464487034949,
|
| 1194 |
+
"eval_runtime": 21.8673,
|
| 1195 |
+
"eval_samples_per_second": 81.126,
|
| 1196 |
+
"eval_steps_per_second": 1.28,
|
| 1197 |
+
"step": 1500
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 24.16,
|
| 1201 |
+
"learning_rate": 2.0908004778972523e-05,
|
| 1202 |
+
"loss": 1.2444,
|
| 1203 |
+
"step": 1510
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 24.32,
|
| 1207 |
+
"learning_rate": 2.031063321385902e-05,
|
| 1208 |
+
"loss": 1.2116,
|
| 1209 |
+
"step": 1520
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 24.48,
|
| 1213 |
+
"learning_rate": 1.9713261648745522e-05,
|
| 1214 |
+
"loss": 1.2061,
|
| 1215 |
+
"step": 1530
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 24.64,
|
| 1219 |
+
"learning_rate": 1.9115890083632022e-05,
|
| 1220 |
+
"loss": 1.2072,
|
| 1221 |
+
"step": 1540
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 24.8,
|
| 1225 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1226 |
+
"loss": 1.2144,
|
| 1227 |
+
"step": 1550
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 24.96,
|
| 1231 |
+
"learning_rate": 1.7921146953405018e-05,
|
| 1232 |
+
"loss": 1.2442,
|
| 1233 |
+
"step": 1560
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 24.99,
|
| 1237 |
+
"eval_accuracy": 0.5913190529875987,
|
| 1238 |
+
"eval_f1": 0.5672449138626566,
|
| 1239 |
+
"eval_loss": 1.1695806980133057,
|
| 1240 |
+
"eval_precision": 0.6061531146445093,
|
| 1241 |
+
"eval_recall": 0.5913190529875987,
|
| 1242 |
+
"eval_runtime": 21.8809,
|
| 1243 |
+
"eval_samples_per_second": 81.075,
|
| 1244 |
+
"eval_steps_per_second": 1.28,
|
| 1245 |
+
"step": 1562
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 25.12,
|
| 1249 |
+
"learning_rate": 1.7323775388291518e-05,
|
| 1250 |
+
"loss": 1.2032,
|
| 1251 |
+
"step": 1570
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 25.28,
|
| 1255 |
+
"learning_rate": 1.6726403823178017e-05,
|
| 1256 |
+
"loss": 1.22,
|
| 1257 |
+
"step": 1580
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 25.44,
|
| 1261 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 1262 |
+
"loss": 1.2206,
|
| 1263 |
+
"step": 1590
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 25.6,
|
| 1267 |
+
"learning_rate": 1.5531660692951016e-05,
|
| 1268 |
+
"loss": 1.2222,
|
| 1269 |
+
"step": 1600
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 25.76,
|
| 1273 |
+
"learning_rate": 1.4934289127837516e-05,
|
| 1274 |
+
"loss": 1.2218,
|
| 1275 |
+
"step": 1610
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 25.92,
|
| 1279 |
+
"learning_rate": 1.4336917562724014e-05,
|
| 1280 |
+
"loss": 1.1913,
|
| 1281 |
+
"step": 1620
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 26.0,
|
| 1285 |
+
"eval_accuracy": 0.5918827508455468,
|
| 1286 |
+
"eval_f1": 0.5677595343942556,
|
| 1287 |
+
"eval_loss": 1.166059970855713,
|
| 1288 |
+
"eval_precision": 0.6011740510143309,
|
| 1289 |
+
"eval_recall": 0.5918827508455468,
|
| 1290 |
+
"eval_runtime": 24.7186,
|
| 1291 |
+
"eval_samples_per_second": 71.768,
|
| 1292 |
+
"eval_steps_per_second": 1.133,
|
| 1293 |
+
"step": 1625
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 26.08,
|
| 1297 |
+
"learning_rate": 1.3739545997610515e-05,
|
| 1298 |
+
"loss": 1.2119,
|
| 1299 |
+
"step": 1630
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 26.24,
|
| 1303 |
+
"learning_rate": 1.3142174432497015e-05,
|
| 1304 |
+
"loss": 1.2229,
|
| 1305 |
+
"step": 1640
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 26.4,
|
| 1309 |
+
"learning_rate": 1.2544802867383513e-05,
|
| 1310 |
+
"loss": 1.2139,
|
| 1311 |
+
"step": 1650
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 26.56,
|
| 1315 |
+
"learning_rate": 1.1947431302270013e-05,
|
| 1316 |
+
"loss": 1.228,
|
| 1317 |
+
"step": 1660
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 26.72,
|
| 1321 |
+
"learning_rate": 1.135005973715651e-05,
|
| 1322 |
+
"loss": 1.2139,
|
| 1323 |
+
"step": 1670
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 26.88,
|
| 1327 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 1328 |
+
"loss": 1.2111,
|
| 1329 |
+
"step": 1680
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 26.99,
|
| 1333 |
+
"eval_accuracy": 0.5941375422773394,
|
| 1334 |
+
"eval_f1": 0.5702300711030653,
|
| 1335 |
+
"eval_loss": 1.1638890504837036,
|
| 1336 |
+
"eval_precision": 0.6024395376181177,
|
| 1337 |
+
"eval_recall": 0.5941375422773394,
|
| 1338 |
+
"eval_runtime": 21.6884,
|
| 1339 |
+
"eval_samples_per_second": 81.795,
|
| 1340 |
+
"eval_steps_per_second": 1.291,
|
| 1341 |
+
"step": 1687
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 27.04,
|
| 1345 |
+
"learning_rate": 1.015531660692951e-05,
|
| 1346 |
+
"loss": 1.2022,
|
| 1347 |
+
"step": 1690
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 27.2,
|
| 1351 |
+
"learning_rate": 9.557945041816011e-06,
|
| 1352 |
+
"loss": 1.2367,
|
| 1353 |
+
"step": 1700
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 27.36,
|
| 1357 |
+
"learning_rate": 8.960573476702509e-06,
|
| 1358 |
+
"loss": 1.2098,
|
| 1359 |
+
"step": 1710
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 27.52,
|
| 1363 |
+
"learning_rate": 8.363201911589009e-06,
|
| 1364 |
+
"loss": 1.2068,
|
| 1365 |
+
"step": 1720
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 27.68,
|
| 1369 |
+
"learning_rate": 7.765830346475508e-06,
|
| 1370 |
+
"loss": 1.2094,
|
| 1371 |
+
"step": 1730
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 27.84,
|
| 1375 |
+
"learning_rate": 7.168458781362007e-06,
|
| 1376 |
+
"loss": 1.2081,
|
| 1377 |
+
"step": 1740
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 28.0,
|
| 1381 |
+
"learning_rate": 6.5710872162485075e-06,
|
| 1382 |
+
"loss": 1.2168,
|
| 1383 |
+
"step": 1750
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 28.0,
|
| 1387 |
+
"eval_accuracy": 0.5952649379932357,
|
| 1388 |
+
"eval_f1": 0.5714376467349129,
|
| 1389 |
+
"eval_loss": 1.1634987592697144,
|
| 1390 |
+
"eval_precision": 0.6038590156410394,
|
| 1391 |
+
"eval_recall": 0.5952649379932357,
|
| 1392 |
+
"eval_runtime": 21.7656,
|
| 1393 |
+
"eval_samples_per_second": 81.505,
|
| 1394 |
+
"eval_steps_per_second": 1.286,
|
| 1395 |
+
"step": 1750
|
| 1396 |
+
}
|
| 1397 |
+
],
|
| 1398 |
+
"logging_steps": 10,
|
| 1399 |
+
"max_steps": 1860,
|
| 1400 |
+
"num_input_tokens_seen": 0,
|
| 1401 |
+
"num_train_epochs": 30,
|
| 1402 |
+
"save_steps": 500,
|
| 1403 |
+
"total_flos": 1.0292439065612098e+20,
|
| 1404 |
+
"train_batch_size": 64,
|
| 1405 |
+
"trial_name": null,
|
| 1406 |
+
"trial_params": null
|
| 1407 |
+
}
|
checkpoint-1750/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1ad4e694ae30159860a2ce22530b0bf3e812fe826a5ba3bca685868e02e3575
|
| 3 |
+
size 4920
|
config.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Swinv2ForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"depths": [
|
| 8 |
+
2,
|
| 9 |
+
2,
|
| 10 |
+
18,
|
| 11 |
+
2
|
| 12 |
+
],
|
| 13 |
+
"drop_path_rate": 0.1,
|
| 14 |
+
"embed_dim": 192,
|
| 15 |
+
"encoder_stride": 32,
|
| 16 |
+
"hidden_act": "gelu",
|
| 17 |
+
"hidden_dropout_prob": 0.0,
|
| 18 |
+
"hidden_size": 1536,
|
| 19 |
+
"id2label": {
|
| 20 |
+
"0": "Disturbed Galaxies",
|
| 21 |
+
"1": "Merging Galaxies",
|
| 22 |
+
"2": "Round Smooth Galaxies",
|
| 23 |
+
"3": "In-between Round Smooth Galaxies",
|
| 24 |
+
"4": "Cigar Shaped Smooth Galaxies",
|
| 25 |
+
"5": "Barred Spiral Galaxies",
|
| 26 |
+
"6": "Unbarred Tight Spiral Galaxies",
|
| 27 |
+
"7": "Unbarred Loose Spiral Galaxies",
|
| 28 |
+
"8": "Edge-on Galaxies without Bulge",
|
| 29 |
+
"9": "Edge-on Galaxies with Bulge"
|
| 30 |
+
},
|
| 31 |
+
"image_size": 256,
|
| 32 |
+
"initializer_range": 0.02,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"Barred Spiral Galaxies": 5,
|
| 35 |
+
"Cigar Shaped Smooth Galaxies": 4,
|
| 36 |
+
"Disturbed Galaxies": 0,
|
| 37 |
+
"Edge-on Galaxies with Bulge": 9,
|
| 38 |
+
"Edge-on Galaxies without Bulge": 8,
|
| 39 |
+
"In-between Round Smooth Galaxies": 3,
|
| 40 |
+
"Merging Galaxies": 1,
|
| 41 |
+
"Round Smooth Galaxies": 2,
|
| 42 |
+
"Unbarred Loose Spiral Galaxies": 7,
|
| 43 |
+
"Unbarred Tight Spiral Galaxies": 6
|
| 44 |
+
},
|
| 45 |
+
"layer_norm_eps": 1e-05,
|
| 46 |
+
"mlp_ratio": 4.0,
|
| 47 |
+
"model_type": "swinv2",
|
| 48 |
+
"num_channels": 3,
|
| 49 |
+
"num_heads": [
|
| 50 |
+
6,
|
| 51 |
+
12,
|
| 52 |
+
24,
|
| 53 |
+
48
|
| 54 |
+
],
|
| 55 |
+
"num_layers": 4,
|
| 56 |
+
"out_features": [
|
| 57 |
+
"stage4"
|
| 58 |
+
],
|
| 59 |
+
"out_indices": [
|
| 60 |
+
4
|
| 61 |
+
],
|
| 62 |
+
"patch_size": 4,
|
| 63 |
+
"path_norm": true,
|
| 64 |
+
"pretrained_window_sizes": [
|
| 65 |
+
12,
|
| 66 |
+
12,
|
| 67 |
+
12,
|
| 68 |
+
6
|
| 69 |
+
],
|
| 70 |
+
"problem_type": "single_label_classification",
|
| 71 |
+
"qkv_bias": true,
|
| 72 |
+
"stage_names": [
|
| 73 |
+
"stem",
|
| 74 |
+
"stage1",
|
| 75 |
+
"stage2",
|
| 76 |
+
"stage3",
|
| 77 |
+
"stage4"
|
| 78 |
+
],
|
| 79 |
+
"torch_dtype": "float32",
|
| 80 |
+
"transformers_version": "4.37.2",
|
| 81 |
+
"use_absolute_embeddings": false,
|
| 82 |
+
"window_size": 16
|
| 83 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"eval_accuracy": 0.5952649379932357,
|
| 4 |
+
"eval_f1": 0.5714376467349129,
|
| 5 |
+
"eval_loss": 1.1634987592697144,
|
| 6 |
+
"eval_precision": 0.6038590156410394,
|
| 7 |
+
"eval_recall": 0.5952649379932357,
|
| 8 |
+
"eval_runtime": 21.9981,
|
| 9 |
+
"eval_samples_per_second": 80.643,
|
| 10 |
+
"eval_steps_per_second": 1.273
|
| 11 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9df592770c26f76c77206bba25c3bd9e563d16dda5c26de88a6e023415e2ffc3
|
| 3 |
+
size 780935472
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.485,
|
| 7 |
+
0.456,
|
| 8 |
+
0.406
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.229,
|
| 13 |
+
0.224,
|
| 14 |
+
0.225
|
| 15 |
+
],
|
| 16 |
+
"resample": 3,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 256,
|
| 20 |
+
"width": 256
|
| 21 |
+
}
|
| 22 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 29.76,
|
| 3 |
+
"train_loss": 1.3704575569398942,
|
| 4 |
+
"train_runtime": 8385.7458,
|
| 5 |
+
"train_samples_per_second": 57.104,
|
| 6 |
+
"train_steps_per_second": 0.222
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1506 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5952649379932357,
|
| 3 |
+
"best_model_checkpoint": "swinv2-large-patch4-window12to16-192to256-22kto1k-ft-head-finetuned-galaxy10-decals/checkpoint-1750",
|
| 4 |
+
"epoch": 29.76,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1860,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"learning_rate": 5.376344086021506e-06,
|
| 14 |
+
"loss": 2.4183,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.32,
|
| 19 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 20 |
+
"loss": 2.3949,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.48,
|
| 25 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 26 |
+
"loss": 2.3777,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.64,
|
| 31 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 32 |
+
"loss": 2.335,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.8,
|
| 37 |
+
"learning_rate": 2.6881720430107527e-05,
|
| 38 |
+
"loss": 2.2929,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.96,
|
| 43 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 44 |
+
"loss": 2.2152,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.99,
|
| 49 |
+
"eval_accuracy": 0.20349492671927846,
|
| 50 |
+
"eval_f1": 0.15105203129445105,
|
| 51 |
+
"eval_loss": 2.188288927078247,
|
| 52 |
+
"eval_precision": 0.14895878509992708,
|
| 53 |
+
"eval_recall": 0.20349492671927846,
|
| 54 |
+
"eval_runtime": 22.1815,
|
| 55 |
+
"eval_samples_per_second": 79.976,
|
| 56 |
+
"eval_steps_per_second": 1.262,
|
| 57 |
+
"step": 62
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.12,
|
| 61 |
+
"learning_rate": 3.763440860215054e-05,
|
| 62 |
+
"loss": 2.1913,
|
| 63 |
+
"step": 70
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.28,
|
| 67 |
+
"learning_rate": 4.301075268817205e-05,
|
| 68 |
+
"loss": 2.1422,
|
| 69 |
+
"step": 80
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.44,
|
| 73 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 74 |
+
"loss": 2.0878,
|
| 75 |
+
"step": 90
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.6,
|
| 79 |
+
"learning_rate": 5.3763440860215054e-05,
|
| 80 |
+
"loss": 2.0411,
|
| 81 |
+
"step": 100
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.76,
|
| 85 |
+
"learning_rate": 5.913978494623657e-05,
|
| 86 |
+
"loss": 1.9976,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.92,
|
| 91 |
+
"learning_rate": 6.451612903225807e-05,
|
| 92 |
+
"loss": 1.9434,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 2.0,
|
| 97 |
+
"eval_accuracy": 0.3506200676437429,
|
| 98 |
+
"eval_f1": 0.272465935568218,
|
| 99 |
+
"eval_loss": 1.9051553010940552,
|
| 100 |
+
"eval_precision": 0.39556561793778316,
|
| 101 |
+
"eval_recall": 0.3506200676437429,
|
| 102 |
+
"eval_runtime": 22.0737,
|
| 103 |
+
"eval_samples_per_second": 80.367,
|
| 104 |
+
"eval_steps_per_second": 1.268,
|
| 105 |
+
"step": 125
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.08,
|
| 109 |
+
"learning_rate": 6.989247311827958e-05,
|
| 110 |
+
"loss": 1.8905,
|
| 111 |
+
"step": 130
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.24,
|
| 115 |
+
"learning_rate": 7.526881720430108e-05,
|
| 116 |
+
"loss": 1.8585,
|
| 117 |
+
"step": 140
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 2.4,
|
| 121 |
+
"learning_rate": 8.064516129032258e-05,
|
| 122 |
+
"loss": 1.814,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.56,
|
| 127 |
+
"learning_rate": 8.60215053763441e-05,
|
| 128 |
+
"loss": 1.8007,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.72,
|
| 133 |
+
"learning_rate": 9.13978494623656e-05,
|
| 134 |
+
"loss": 1.7578,
|
| 135 |
+
"step": 170
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.88,
|
| 139 |
+
"learning_rate": 9.677419354838711e-05,
|
| 140 |
+
"loss": 1.7295,
|
| 141 |
+
"step": 180
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.99,
|
| 145 |
+
"eval_accuracy": 0.4368658399098083,
|
| 146 |
+
"eval_f1": 0.3915006667744191,
|
| 147 |
+
"eval_loss": 1.6789493560791016,
|
| 148 |
+
"eval_precision": 0.46298297663493393,
|
| 149 |
+
"eval_recall": 0.4368658399098083,
|
| 150 |
+
"eval_runtime": 22.0192,
|
| 151 |
+
"eval_samples_per_second": 80.566,
|
| 152 |
+
"eval_steps_per_second": 1.272,
|
| 153 |
+
"step": 187
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 3.04,
|
| 157 |
+
"learning_rate": 9.97610513739546e-05,
|
| 158 |
+
"loss": 1.7217,
|
| 159 |
+
"step": 190
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.2,
|
| 163 |
+
"learning_rate": 9.916367980884111e-05,
|
| 164 |
+
"loss": 1.6519,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.36,
|
| 169 |
+
"learning_rate": 9.85663082437276e-05,
|
| 170 |
+
"loss": 1.6417,
|
| 171 |
+
"step": 210
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 3.52,
|
| 175 |
+
"learning_rate": 9.79689366786141e-05,
|
| 176 |
+
"loss": 1.6192,
|
| 177 |
+
"step": 220
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 3.68,
|
| 181 |
+
"learning_rate": 9.73715651135006e-05,
|
| 182 |
+
"loss": 1.6046,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.84,
|
| 187 |
+
"learning_rate": 9.677419354838711e-05,
|
| 188 |
+
"loss": 1.5931,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.0,
|
| 193 |
+
"learning_rate": 9.61768219832736e-05,
|
| 194 |
+
"loss": 1.5541,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.0,
|
| 199 |
+
"eval_accuracy": 0.47576099210823,
|
| 200 |
+
"eval_f1": 0.4335867277644615,
|
| 201 |
+
"eval_loss": 1.5338377952575684,
|
| 202 |
+
"eval_precision": 0.509541084219624,
|
| 203 |
+
"eval_recall": 0.47576099210823,
|
| 204 |
+
"eval_runtime": 22.1469,
|
| 205 |
+
"eval_samples_per_second": 80.102,
|
| 206 |
+
"eval_steps_per_second": 1.264,
|
| 207 |
+
"step": 250
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 4.16,
|
| 211 |
+
"learning_rate": 9.55794504181601e-05,
|
| 212 |
+
"loss": 1.5557,
|
| 213 |
+
"step": 260
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 4.32,
|
| 217 |
+
"learning_rate": 9.49820788530466e-05,
|
| 218 |
+
"loss": 1.5259,
|
| 219 |
+
"step": 270
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 4.48,
|
| 223 |
+
"learning_rate": 9.438470728793309e-05,
|
| 224 |
+
"loss": 1.5044,
|
| 225 |
+
"step": 280
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 4.64,
|
| 229 |
+
"learning_rate": 9.378733572281961e-05,
|
| 230 |
+
"loss": 1.5017,
|
| 231 |
+
"step": 290
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 4.8,
|
| 235 |
+
"learning_rate": 9.31899641577061e-05,
|
| 236 |
+
"loss": 1.4979,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 4.96,
|
| 241 |
+
"learning_rate": 9.25925925925926e-05,
|
| 242 |
+
"loss": 1.4558,
|
| 243 |
+
"step": 310
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 4.99,
|
| 247 |
+
"eval_accuracy": 0.520293122886133,
|
| 248 |
+
"eval_f1": 0.48596376905849764,
|
| 249 |
+
"eval_loss": 1.4501919746398926,
|
| 250 |
+
"eval_precision": 0.5414266437447433,
|
| 251 |
+
"eval_recall": 0.520293122886133,
|
| 252 |
+
"eval_runtime": 22.0839,
|
| 253 |
+
"eval_samples_per_second": 80.33,
|
| 254 |
+
"eval_steps_per_second": 1.268,
|
| 255 |
+
"step": 312
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 5.12,
|
| 259 |
+
"learning_rate": 9.199522102747909e-05,
|
| 260 |
+
"loss": 1.4861,
|
| 261 |
+
"step": 320
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 5.28,
|
| 265 |
+
"learning_rate": 9.13978494623656e-05,
|
| 266 |
+
"loss": 1.4779,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 5.44,
|
| 271 |
+
"learning_rate": 9.080047789725208e-05,
|
| 272 |
+
"loss": 1.4526,
|
| 273 |
+
"step": 340
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 5.6,
|
| 277 |
+
"learning_rate": 9.02031063321386e-05,
|
| 278 |
+
"loss": 1.4667,
|
| 279 |
+
"step": 350
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 5.76,
|
| 283 |
+
"learning_rate": 8.960573476702509e-05,
|
| 284 |
+
"loss": 1.4395,
|
| 285 |
+
"step": 360
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 5.92,
|
| 289 |
+
"learning_rate": 8.900836320191159e-05,
|
| 290 |
+
"loss": 1.42,
|
| 291 |
+
"step": 370
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 6.0,
|
| 295 |
+
"eval_accuracy": 0.520293122886133,
|
| 296 |
+
"eval_f1": 0.4892009598786175,
|
| 297 |
+
"eval_loss": 1.399051308631897,
|
| 298 |
+
"eval_precision": 0.5529206104546609,
|
| 299 |
+
"eval_recall": 0.520293122886133,
|
| 300 |
+
"eval_runtime": 22.0309,
|
| 301 |
+
"eval_samples_per_second": 80.523,
|
| 302 |
+
"eval_steps_per_second": 1.271,
|
| 303 |
+
"step": 375
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 6.08,
|
| 307 |
+
"learning_rate": 8.84109916367981e-05,
|
| 308 |
+
"loss": 1.4285,
|
| 309 |
+
"step": 380
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.24,
|
| 313 |
+
"learning_rate": 8.781362007168459e-05,
|
| 314 |
+
"loss": 1.4283,
|
| 315 |
+
"step": 390
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 6.4,
|
| 319 |
+
"learning_rate": 8.72162485065711e-05,
|
| 320 |
+
"loss": 1.3969,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 6.56,
|
| 325 |
+
"learning_rate": 8.661887694145759e-05,
|
| 326 |
+
"loss": 1.4135,
|
| 327 |
+
"step": 410
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 6.72,
|
| 331 |
+
"learning_rate": 8.60215053763441e-05,
|
| 332 |
+
"loss": 1.3878,
|
| 333 |
+
"step": 420
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 6.88,
|
| 337 |
+
"learning_rate": 8.542413381123058e-05,
|
| 338 |
+
"loss": 1.3806,
|
| 339 |
+
"step": 430
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 6.99,
|
| 343 |
+
"eval_accuracy": 0.5501691093573844,
|
| 344 |
+
"eval_f1": 0.5227011346941011,
|
| 345 |
+
"eval_loss": 1.3529337644577026,
|
| 346 |
+
"eval_precision": 0.5732264535553914,
|
| 347 |
+
"eval_recall": 0.5501691093573844,
|
| 348 |
+
"eval_runtime": 22.1773,
|
| 349 |
+
"eval_samples_per_second": 79.992,
|
| 350 |
+
"eval_steps_per_second": 1.263,
|
| 351 |
+
"step": 437
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 7.04,
|
| 355 |
+
"learning_rate": 8.482676224611709e-05,
|
| 356 |
+
"loss": 1.4184,
|
| 357 |
+
"step": 440
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 7.2,
|
| 361 |
+
"learning_rate": 8.422939068100359e-05,
|
| 362 |
+
"loss": 1.4169,
|
| 363 |
+
"step": 450
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 7.36,
|
| 367 |
+
"learning_rate": 8.363201911589009e-05,
|
| 368 |
+
"loss": 1.3882,
|
| 369 |
+
"step": 460
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 7.52,
|
| 373 |
+
"learning_rate": 8.30346475507766e-05,
|
| 374 |
+
"loss": 1.3869,
|
| 375 |
+
"step": 470
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 7.68,
|
| 379 |
+
"learning_rate": 8.243727598566309e-05,
|
| 380 |
+
"loss": 1.3499,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 7.84,
|
| 385 |
+
"learning_rate": 8.183990442054959e-05,
|
| 386 |
+
"loss": 1.3531,
|
| 387 |
+
"step": 490
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 8.0,
|
| 391 |
+
"learning_rate": 8.124253285543608e-05,
|
| 392 |
+
"loss": 1.3541,
|
| 393 |
+
"step": 500
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 8.0,
|
| 397 |
+
"eval_accuracy": 0.560315670800451,
|
| 398 |
+
"eval_f1": 0.532522788067071,
|
| 399 |
+
"eval_loss": 1.3217679262161255,
|
| 400 |
+
"eval_precision": 0.5934036230328783,
|
| 401 |
+
"eval_recall": 0.560315670800451,
|
| 402 |
+
"eval_runtime": 22.0874,
|
| 403 |
+
"eval_samples_per_second": 80.317,
|
| 404 |
+
"eval_steps_per_second": 1.268,
|
| 405 |
+
"step": 500
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 8.16,
|
| 409 |
+
"learning_rate": 8.064516129032258e-05,
|
| 410 |
+
"loss": 1.3568,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 8.32,
|
| 415 |
+
"learning_rate": 8.004778972520908e-05,
|
| 416 |
+
"loss": 1.3505,
|
| 417 |
+
"step": 520
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 8.48,
|
| 421 |
+
"learning_rate": 7.945041816009559e-05,
|
| 422 |
+
"loss": 1.397,
|
| 423 |
+
"step": 530
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 8.64,
|
| 427 |
+
"learning_rate": 7.885304659498209e-05,
|
| 428 |
+
"loss": 1.3614,
|
| 429 |
+
"step": 540
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 8.8,
|
| 433 |
+
"learning_rate": 7.825567502986858e-05,
|
| 434 |
+
"loss": 1.3543,
|
| 435 |
+
"step": 550
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 8.96,
|
| 439 |
+
"learning_rate": 7.765830346475508e-05,
|
| 440 |
+
"loss": 1.337,
|
| 441 |
+
"step": 560
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 8.99,
|
| 445 |
+
"eval_accuracy": 0.5597519729425028,
|
| 446 |
+
"eval_f1": 0.5304260590298405,
|
| 447 |
+
"eval_loss": 1.3014049530029297,
|
| 448 |
+
"eval_precision": 0.6007885455628412,
|
| 449 |
+
"eval_recall": 0.5597519729425028,
|
| 450 |
+
"eval_runtime": 22.0361,
|
| 451 |
+
"eval_samples_per_second": 80.504,
|
| 452 |
+
"eval_steps_per_second": 1.271,
|
| 453 |
+
"step": 562
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 9.12,
|
| 457 |
+
"learning_rate": 7.706093189964157e-05,
|
| 458 |
+
"loss": 1.359,
|
| 459 |
+
"step": 570
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 9.28,
|
| 463 |
+
"learning_rate": 7.646356033452809e-05,
|
| 464 |
+
"loss": 1.3222,
|
| 465 |
+
"step": 580
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 9.44,
|
| 469 |
+
"learning_rate": 7.586618876941458e-05,
|
| 470 |
+
"loss": 1.3325,
|
| 471 |
+
"step": 590
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 9.6,
|
| 475 |
+
"learning_rate": 7.526881720430108e-05,
|
| 476 |
+
"loss": 1.3524,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 9.76,
|
| 481 |
+
"learning_rate": 7.467144563918757e-05,
|
| 482 |
+
"loss": 1.3077,
|
| 483 |
+
"step": 610
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 9.92,
|
| 487 |
+
"learning_rate": 7.407407407407407e-05,
|
| 488 |
+
"loss": 1.3164,
|
| 489 |
+
"step": 620
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 10.0,
|
| 493 |
+
"eval_accuracy": 0.5552423900789177,
|
| 494 |
+
"eval_f1": 0.5269514020319623,
|
| 495 |
+
"eval_loss": 1.285463571548462,
|
| 496 |
+
"eval_precision": 0.5617951310681798,
|
| 497 |
+
"eval_recall": 0.5552423900789177,
|
| 498 |
+
"eval_runtime": 22.0709,
|
| 499 |
+
"eval_samples_per_second": 80.377,
|
| 500 |
+
"eval_steps_per_second": 1.269,
|
| 501 |
+
"step": 625
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 10.08,
|
| 505 |
+
"learning_rate": 7.347670250896058e-05,
|
| 506 |
+
"loss": 1.336,
|
| 507 |
+
"step": 630
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 10.24,
|
| 511 |
+
"learning_rate": 7.287933094384708e-05,
|
| 512 |
+
"loss": 1.3231,
|
| 513 |
+
"step": 640
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 10.4,
|
| 517 |
+
"learning_rate": 7.228195937873358e-05,
|
| 518 |
+
"loss": 1.3111,
|
| 519 |
+
"step": 650
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 10.56,
|
| 523 |
+
"learning_rate": 7.168458781362007e-05,
|
| 524 |
+
"loss": 1.3081,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 10.72,
|
| 529 |
+
"learning_rate": 7.108721624850657e-05,
|
| 530 |
+
"loss": 1.2971,
|
| 531 |
+
"step": 670
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 10.88,
|
| 535 |
+
"learning_rate": 7.048984468339306e-05,
|
| 536 |
+
"loss": 1.2904,
|
| 537 |
+
"step": 680
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 10.99,
|
| 541 |
+
"eval_accuracy": 0.5715896279594137,
|
| 542 |
+
"eval_f1": 0.544321340926892,
|
| 543 |
+
"eval_loss": 1.2624871730804443,
|
| 544 |
+
"eval_precision": 0.6199672961362004,
|
| 545 |
+
"eval_recall": 0.5715896279594137,
|
| 546 |
+
"eval_runtime": 22.0129,
|
| 547 |
+
"eval_samples_per_second": 80.589,
|
| 548 |
+
"eval_steps_per_second": 1.272,
|
| 549 |
+
"step": 687
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 11.04,
|
| 553 |
+
"learning_rate": 6.989247311827958e-05,
|
| 554 |
+
"loss": 1.3266,
|
| 555 |
+
"step": 690
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 11.2,
|
| 559 |
+
"learning_rate": 6.929510155316607e-05,
|
| 560 |
+
"loss": 1.3018,
|
| 561 |
+
"step": 700
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 11.36,
|
| 565 |
+
"learning_rate": 6.869772998805257e-05,
|
| 566 |
+
"loss": 1.2864,
|
| 567 |
+
"step": 710
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 11.52,
|
| 571 |
+
"learning_rate": 6.810035842293908e-05,
|
| 572 |
+
"loss": 1.3119,
|
| 573 |
+
"step": 720
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 11.68,
|
| 577 |
+
"learning_rate": 6.750298685782557e-05,
|
| 578 |
+
"loss": 1.2891,
|
| 579 |
+
"step": 730
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 11.84,
|
| 583 |
+
"learning_rate": 6.690561529271207e-05,
|
| 584 |
+
"loss": 1.2815,
|
| 585 |
+
"step": 740
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 12.0,
|
| 589 |
+
"learning_rate": 6.630824372759857e-05,
|
| 590 |
+
"loss": 1.2873,
|
| 591 |
+
"step": 750
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 12.0,
|
| 595 |
+
"eval_accuracy": 0.5698985343855694,
|
| 596 |
+
"eval_f1": 0.5446306363255216,
|
| 597 |
+
"eval_loss": 1.248738169670105,
|
| 598 |
+
"eval_precision": 0.5943470885639225,
|
| 599 |
+
"eval_recall": 0.5698985343855694,
|
| 600 |
+
"eval_runtime": 21.9956,
|
| 601 |
+
"eval_samples_per_second": 80.653,
|
| 602 |
+
"eval_steps_per_second": 1.273,
|
| 603 |
+
"step": 750
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 12.16,
|
| 607 |
+
"learning_rate": 6.571087216248507e-05,
|
| 608 |
+
"loss": 1.2642,
|
| 609 |
+
"step": 760
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 12.32,
|
| 613 |
+
"learning_rate": 6.511350059737156e-05,
|
| 614 |
+
"loss": 1.2815,
|
| 615 |
+
"step": 770
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 12.48,
|
| 619 |
+
"learning_rate": 6.451612903225807e-05,
|
| 620 |
+
"loss": 1.2987,
|
| 621 |
+
"step": 780
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 12.64,
|
| 625 |
+
"learning_rate": 6.391875746714456e-05,
|
| 626 |
+
"loss": 1.2964,
|
| 627 |
+
"step": 790
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 12.8,
|
| 631 |
+
"learning_rate": 6.332138590203107e-05,
|
| 632 |
+
"loss": 1.2946,
|
| 633 |
+
"step": 800
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 12.96,
|
| 637 |
+
"learning_rate": 6.272401433691756e-05,
|
| 638 |
+
"loss": 1.2911,
|
| 639 |
+
"step": 810
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 12.99,
|
| 643 |
+
"eval_accuracy": 0.5772266065388951,
|
| 644 |
+
"eval_f1": 0.5531271982911073,
|
| 645 |
+
"eval_loss": 1.2366129159927368,
|
| 646 |
+
"eval_precision": 0.6023489690717835,
|
| 647 |
+
"eval_recall": 0.5772266065388951,
|
| 648 |
+
"eval_runtime": 22.1699,
|
| 649 |
+
"eval_samples_per_second": 80.019,
|
| 650 |
+
"eval_steps_per_second": 1.263,
|
| 651 |
+
"step": 812
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 13.12,
|
| 655 |
+
"learning_rate": 6.212664277180407e-05,
|
| 656 |
+
"loss": 1.2581,
|
| 657 |
+
"step": 820
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 13.28,
|
| 661 |
+
"learning_rate": 6.152927120669057e-05,
|
| 662 |
+
"loss": 1.2737,
|
| 663 |
+
"step": 830
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 13.44,
|
| 667 |
+
"learning_rate": 6.093189964157706e-05,
|
| 668 |
+
"loss": 1.2834,
|
| 669 |
+
"step": 840
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 13.6,
|
| 673 |
+
"learning_rate": 6.033452807646356e-05,
|
| 674 |
+
"loss": 1.2522,
|
| 675 |
+
"step": 850
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 13.76,
|
| 679 |
+
"learning_rate": 5.9737156511350064e-05,
|
| 680 |
+
"loss": 1.2698,
|
| 681 |
+
"step": 860
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 13.92,
|
| 685 |
+
"learning_rate": 5.913978494623657e-05,
|
| 686 |
+
"loss": 1.2723,
|
| 687 |
+
"step": 870
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 14.0,
|
| 691 |
+
"eval_accuracy": 0.5817361894024803,
|
| 692 |
+
"eval_f1": 0.55938608951765,
|
| 693 |
+
"eval_loss": 1.2241930961608887,
|
| 694 |
+
"eval_precision": 0.5945742291844911,
|
| 695 |
+
"eval_recall": 0.5817361894024803,
|
| 696 |
+
"eval_runtime": 21.9188,
|
| 697 |
+
"eval_samples_per_second": 80.935,
|
| 698 |
+
"eval_steps_per_second": 1.277,
|
| 699 |
+
"step": 875
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 14.08,
|
| 703 |
+
"learning_rate": 5.8542413381123063e-05,
|
| 704 |
+
"loss": 1.2748,
|
| 705 |
+
"step": 880
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 14.24,
|
| 709 |
+
"learning_rate": 5.794504181600956e-05,
|
| 710 |
+
"loss": 1.2495,
|
| 711 |
+
"step": 890
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 14.4,
|
| 715 |
+
"learning_rate": 5.7347670250896056e-05,
|
| 716 |
+
"loss": 1.2677,
|
| 717 |
+
"step": 900
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 14.56,
|
| 721 |
+
"learning_rate": 5.675029868578255e-05,
|
| 722 |
+
"loss": 1.265,
|
| 723 |
+
"step": 910
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 14.72,
|
| 727 |
+
"learning_rate": 5.615292712066906e-05,
|
| 728 |
+
"loss": 1.2726,
|
| 729 |
+
"step": 920
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 14.88,
|
| 733 |
+
"learning_rate": 5.555555555555556e-05,
|
| 734 |
+
"loss": 1.2527,
|
| 735 |
+
"step": 930
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 14.99,
|
| 739 |
+
"eval_accuracy": 0.5822998872604284,
|
| 740 |
+
"eval_f1": 0.5601846765224702,
|
| 741 |
+
"eval_loss": 1.2167905569076538,
|
| 742 |
+
"eval_precision": 0.5957646682172907,
|
| 743 |
+
"eval_recall": 0.5822998872604284,
|
| 744 |
+
"eval_runtime": 22.0356,
|
| 745 |
+
"eval_samples_per_second": 80.506,
|
| 746 |
+
"eval_steps_per_second": 1.271,
|
| 747 |
+
"step": 937
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 15.04,
|
| 751 |
+
"learning_rate": 5.495818399044206e-05,
|
| 752 |
+
"loss": 1.2631,
|
| 753 |
+
"step": 940
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 15.2,
|
| 757 |
+
"learning_rate": 5.436081242532856e-05,
|
| 758 |
+
"loss": 1.2596,
|
| 759 |
+
"step": 950
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 15.36,
|
| 763 |
+
"learning_rate": 5.3763440860215054e-05,
|
| 764 |
+
"loss": 1.257,
|
| 765 |
+
"step": 960
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 15.52,
|
| 769 |
+
"learning_rate": 5.316606929510155e-05,
|
| 770 |
+
"loss": 1.2618,
|
| 771 |
+
"step": 970
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 15.68,
|
| 775 |
+
"learning_rate": 5.256869772998806e-05,
|
| 776 |
+
"loss": 1.2497,
|
| 777 |
+
"step": 980
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 15.84,
|
| 781 |
+
"learning_rate": 5.1971326164874556e-05,
|
| 782 |
+
"loss": 1.2499,
|
| 783 |
+
"step": 990
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 16.0,
|
| 787 |
+
"learning_rate": 5.137395459976105e-05,
|
| 788 |
+
"loss": 1.2692,
|
| 789 |
+
"step": 1000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 16.0,
|
| 793 |
+
"eval_accuracy": 0.5856820744081173,
|
| 794 |
+
"eval_f1": 0.5625146496179491,
|
| 795 |
+
"eval_loss": 1.2087658643722534,
|
| 796 |
+
"eval_precision": 0.6014714549054646,
|
| 797 |
+
"eval_recall": 0.5856820744081173,
|
| 798 |
+
"eval_runtime": 22.0433,
|
| 799 |
+
"eval_samples_per_second": 80.478,
|
| 800 |
+
"eval_steps_per_second": 1.27,
|
| 801 |
+
"step": 1000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 16.16,
|
| 805 |
+
"learning_rate": 5.077658303464755e-05,
|
| 806 |
+
"loss": 1.2429,
|
| 807 |
+
"step": 1010
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 16.32,
|
| 811 |
+
"learning_rate": 5.017921146953405e-05,
|
| 812 |
+
"loss": 1.2498,
|
| 813 |
+
"step": 1020
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 16.48,
|
| 817 |
+
"learning_rate": 4.9581839904420555e-05,
|
| 818 |
+
"loss": 1.2689,
|
| 819 |
+
"step": 1030
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 16.64,
|
| 823 |
+
"learning_rate": 4.898446833930705e-05,
|
| 824 |
+
"loss": 1.2683,
|
| 825 |
+
"step": 1040
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 16.8,
|
| 829 |
+
"learning_rate": 4.8387096774193554e-05,
|
| 830 |
+
"loss": 1.2617,
|
| 831 |
+
"step": 1050
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 16.96,
|
| 835 |
+
"learning_rate": 4.778972520908005e-05,
|
| 836 |
+
"loss": 1.2279,
|
| 837 |
+
"step": 1060
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 16.99,
|
| 841 |
+
"eval_accuracy": 0.5851183765501691,
|
| 842 |
+
"eval_f1": 0.5622039743774847,
|
| 843 |
+
"eval_loss": 1.203583836555481,
|
| 844 |
+
"eval_precision": 0.60014103604046,
|
| 845 |
+
"eval_recall": 0.5851183765501691,
|
| 846 |
+
"eval_runtime": 22.1622,
|
| 847 |
+
"eval_samples_per_second": 80.046,
|
| 848 |
+
"eval_steps_per_second": 1.263,
|
| 849 |
+
"step": 1062
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 17.12,
|
| 853 |
+
"learning_rate": 4.7192353643966546e-05,
|
| 854 |
+
"loss": 1.217,
|
| 855 |
+
"step": 1070
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 17.28,
|
| 859 |
+
"learning_rate": 4.659498207885305e-05,
|
| 860 |
+
"loss": 1.2531,
|
| 861 |
+
"step": 1080
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 17.44,
|
| 865 |
+
"learning_rate": 4.5997610513739546e-05,
|
| 866 |
+
"loss": 1.2634,
|
| 867 |
+
"step": 1090
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 17.6,
|
| 871 |
+
"learning_rate": 4.540023894862604e-05,
|
| 872 |
+
"loss": 1.2465,
|
| 873 |
+
"step": 1100
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 17.76,
|
| 877 |
+
"learning_rate": 4.4802867383512545e-05,
|
| 878 |
+
"loss": 1.2665,
|
| 879 |
+
"step": 1110
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 17.92,
|
| 883 |
+
"learning_rate": 4.420549581839905e-05,
|
| 884 |
+
"loss": 1.2539,
|
| 885 |
+
"step": 1120
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 18.0,
|
| 889 |
+
"eval_accuracy": 0.5822998872604284,
|
| 890 |
+
"eval_f1": 0.5591138810402552,
|
| 891 |
+
"eval_loss": 1.1966551542282104,
|
| 892 |
+
"eval_precision": 0.6010933850255593,
|
| 893 |
+
"eval_recall": 0.5822998872604284,
|
| 894 |
+
"eval_runtime": 22.0507,
|
| 895 |
+
"eval_samples_per_second": 80.451,
|
| 896 |
+
"eval_steps_per_second": 1.27,
|
| 897 |
+
"step": 1125
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 18.08,
|
| 901 |
+
"learning_rate": 4.360812425328555e-05,
|
| 902 |
+
"loss": 1.2355,
|
| 903 |
+
"step": 1130
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 18.24,
|
| 907 |
+
"learning_rate": 4.301075268817205e-05,
|
| 908 |
+
"loss": 1.2481,
|
| 909 |
+
"step": 1140
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 18.4,
|
| 913 |
+
"learning_rate": 4.241338112305854e-05,
|
| 914 |
+
"loss": 1.2128,
|
| 915 |
+
"step": 1150
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 18.56,
|
| 919 |
+
"learning_rate": 4.1816009557945046e-05,
|
| 920 |
+
"loss": 1.2455,
|
| 921 |
+
"step": 1160
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 18.72,
|
| 925 |
+
"learning_rate": 4.121863799283154e-05,
|
| 926 |
+
"loss": 1.2491,
|
| 927 |
+
"step": 1170
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 18.88,
|
| 931 |
+
"learning_rate": 4.062126642771804e-05,
|
| 932 |
+
"loss": 1.2341,
|
| 933 |
+
"step": 1180
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 18.99,
|
| 937 |
+
"eval_accuracy": 0.5907553551296505,
|
| 938 |
+
"eval_f1": 0.5665315520801317,
|
| 939 |
+
"eval_loss": 1.187435269355774,
|
| 940 |
+
"eval_precision": 0.6124355427768795,
|
| 941 |
+
"eval_recall": 0.5907553551296505,
|
| 942 |
+
"eval_runtime": 22.0769,
|
| 943 |
+
"eval_samples_per_second": 80.356,
|
| 944 |
+
"eval_steps_per_second": 1.268,
|
| 945 |
+
"step": 1187
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 19.04,
|
| 949 |
+
"learning_rate": 4.002389486260454e-05,
|
| 950 |
+
"loss": 1.2278,
|
| 951 |
+
"step": 1190
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 19.2,
|
| 955 |
+
"learning_rate": 3.9426523297491045e-05,
|
| 956 |
+
"loss": 1.2442,
|
| 957 |
+
"step": 1200
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 19.36,
|
| 961 |
+
"learning_rate": 3.882915173237754e-05,
|
| 962 |
+
"loss": 1.2192,
|
| 963 |
+
"step": 1210
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 19.52,
|
| 967 |
+
"learning_rate": 3.8231780167264044e-05,
|
| 968 |
+
"loss": 1.2532,
|
| 969 |
+
"step": 1220
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 19.68,
|
| 973 |
+
"learning_rate": 3.763440860215054e-05,
|
| 974 |
+
"loss": 1.2309,
|
| 975 |
+
"step": 1230
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 19.84,
|
| 979 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 980 |
+
"loss": 1.2555,
|
| 981 |
+
"step": 1240
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 20.0,
|
| 985 |
+
"learning_rate": 3.643966547192354e-05,
|
| 986 |
+
"loss": 1.2475,
|
| 987 |
+
"step": 1250
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 20.0,
|
| 991 |
+
"eval_accuracy": 0.584554678692221,
|
| 992 |
+
"eval_f1": 0.5598437529375522,
|
| 993 |
+
"eval_loss": 1.1870439052581787,
|
| 994 |
+
"eval_precision": 0.6019233382358613,
|
| 995 |
+
"eval_recall": 0.584554678692221,
|
| 996 |
+
"eval_runtime": 21.6957,
|
| 997 |
+
"eval_samples_per_second": 81.767,
|
| 998 |
+
"eval_steps_per_second": 1.291,
|
| 999 |
+
"step": 1250
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 20.16,
|
| 1003 |
+
"learning_rate": 3.5842293906810036e-05,
|
| 1004 |
+
"loss": 1.2521,
|
| 1005 |
+
"step": 1260
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 20.32,
|
| 1009 |
+
"learning_rate": 3.524492234169653e-05,
|
| 1010 |
+
"loss": 1.2373,
|
| 1011 |
+
"step": 1270
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 20.48,
|
| 1015 |
+
"learning_rate": 3.4647550776583035e-05,
|
| 1016 |
+
"loss": 1.2188,
|
| 1017 |
+
"step": 1280
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 20.64,
|
| 1021 |
+
"learning_rate": 3.405017921146954e-05,
|
| 1022 |
+
"loss": 1.2398,
|
| 1023 |
+
"step": 1290
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 20.8,
|
| 1027 |
+
"learning_rate": 3.3452807646356034e-05,
|
| 1028 |
+
"loss": 1.2405,
|
| 1029 |
+
"step": 1300
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 20.96,
|
| 1033 |
+
"learning_rate": 3.285543608124254e-05,
|
| 1034 |
+
"loss": 1.2009,
|
| 1035 |
+
"step": 1310
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 20.99,
|
| 1039 |
+
"eval_accuracy": 0.593010146561443,
|
| 1040 |
+
"eval_f1": 0.5691157408882564,
|
| 1041 |
+
"eval_loss": 1.1792354583740234,
|
| 1042 |
+
"eval_precision": 0.6069905496006659,
|
| 1043 |
+
"eval_recall": 0.593010146561443,
|
| 1044 |
+
"eval_runtime": 21.918,
|
| 1045 |
+
"eval_samples_per_second": 80.938,
|
| 1046 |
+
"eval_steps_per_second": 1.277,
|
| 1047 |
+
"step": 1312
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 21.12,
|
| 1051 |
+
"learning_rate": 3.2258064516129034e-05,
|
| 1052 |
+
"loss": 1.2068,
|
| 1053 |
+
"step": 1320
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 21.28,
|
| 1057 |
+
"learning_rate": 3.1660692951015537e-05,
|
| 1058 |
+
"loss": 1.2272,
|
| 1059 |
+
"step": 1330
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 21.44,
|
| 1063 |
+
"learning_rate": 3.106332138590203e-05,
|
| 1064 |
+
"loss": 1.2156,
|
| 1065 |
+
"step": 1340
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 21.6,
|
| 1069 |
+
"learning_rate": 3.046594982078853e-05,
|
| 1070 |
+
"loss": 1.2154,
|
| 1071 |
+
"step": 1350
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 21.76,
|
| 1075 |
+
"learning_rate": 2.9868578255675032e-05,
|
| 1076 |
+
"loss": 1.214,
|
| 1077 |
+
"step": 1360
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 21.92,
|
| 1081 |
+
"learning_rate": 2.9271206690561532e-05,
|
| 1082 |
+
"loss": 1.2515,
|
| 1083 |
+
"step": 1370
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 22.0,
|
| 1087 |
+
"eval_accuracy": 0.5918827508455468,
|
| 1088 |
+
"eval_f1": 0.5678475976802037,
|
| 1089 |
+
"eval_loss": 1.1771893501281738,
|
| 1090 |
+
"eval_precision": 0.606224629917707,
|
| 1091 |
+
"eval_recall": 0.5918827508455468,
|
| 1092 |
+
"eval_runtime": 21.8417,
|
| 1093 |
+
"eval_samples_per_second": 81.221,
|
| 1094 |
+
"eval_steps_per_second": 1.282,
|
| 1095 |
+
"step": 1375
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 22.08,
|
| 1099 |
+
"learning_rate": 2.8673835125448028e-05,
|
| 1100 |
+
"loss": 1.2501,
|
| 1101 |
+
"step": 1380
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 22.24,
|
| 1105 |
+
"learning_rate": 2.807646356033453e-05,
|
| 1106 |
+
"loss": 1.2147,
|
| 1107 |
+
"step": 1390
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 22.4,
|
| 1111 |
+
"learning_rate": 2.747909199522103e-05,
|
| 1112 |
+
"loss": 1.184,
|
| 1113 |
+
"step": 1400
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 22.56,
|
| 1117 |
+
"learning_rate": 2.6881720430107527e-05,
|
| 1118 |
+
"loss": 1.2386,
|
| 1119 |
+
"step": 1410
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 22.72,
|
| 1123 |
+
"learning_rate": 2.628434886499403e-05,
|
| 1124 |
+
"loss": 1.2336,
|
| 1125 |
+
"step": 1420
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 22.88,
|
| 1129 |
+
"learning_rate": 2.5686977299880526e-05,
|
| 1130 |
+
"loss": 1.2361,
|
| 1131 |
+
"step": 1430
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 22.99,
|
| 1135 |
+
"eval_accuracy": 0.5918827508455468,
|
| 1136 |
+
"eval_f1": 0.5680339449025893,
|
| 1137 |
+
"eval_loss": 1.1749292612075806,
|
| 1138 |
+
"eval_precision": 0.6079590653989706,
|
| 1139 |
+
"eval_recall": 0.5918827508455468,
|
| 1140 |
+
"eval_runtime": 21.9917,
|
| 1141 |
+
"eval_samples_per_second": 80.667,
|
| 1142 |
+
"eval_steps_per_second": 1.273,
|
| 1143 |
+
"step": 1437
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 23.04,
|
| 1147 |
+
"learning_rate": 2.5089605734767026e-05,
|
| 1148 |
+
"loss": 1.2493,
|
| 1149 |
+
"step": 1440
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 23.2,
|
| 1153 |
+
"learning_rate": 2.4492234169653525e-05,
|
| 1154 |
+
"loss": 1.2109,
|
| 1155 |
+
"step": 1450
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 23.36,
|
| 1159 |
+
"learning_rate": 2.3894862604540025e-05,
|
| 1160 |
+
"loss": 1.2227,
|
| 1161 |
+
"step": 1460
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 23.52,
|
| 1165 |
+
"learning_rate": 2.3297491039426525e-05,
|
| 1166 |
+
"loss": 1.2163,
|
| 1167 |
+
"step": 1470
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 23.68,
|
| 1171 |
+
"learning_rate": 2.270011947431302e-05,
|
| 1172 |
+
"loss": 1.2372,
|
| 1173 |
+
"step": 1480
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 23.84,
|
| 1177 |
+
"learning_rate": 2.2102747909199524e-05,
|
| 1178 |
+
"loss": 1.1965,
|
| 1179 |
+
"step": 1490
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 24.0,
|
| 1183 |
+
"learning_rate": 2.1505376344086024e-05,
|
| 1184 |
+
"loss": 1.2366,
|
| 1185 |
+
"step": 1500
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 24.0,
|
| 1189 |
+
"eval_accuracy": 0.5924464487034949,
|
| 1190 |
+
"eval_f1": 0.5690711817132577,
|
| 1191 |
+
"eval_loss": 1.1708468198776245,
|
| 1192 |
+
"eval_precision": 0.6047825042790245,
|
| 1193 |
+
"eval_recall": 0.5924464487034949,
|
| 1194 |
+
"eval_runtime": 21.8673,
|
| 1195 |
+
"eval_samples_per_second": 81.126,
|
| 1196 |
+
"eval_steps_per_second": 1.28,
|
| 1197 |
+
"step": 1500
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 24.16,
|
| 1201 |
+
"learning_rate": 2.0908004778972523e-05,
|
| 1202 |
+
"loss": 1.2444,
|
| 1203 |
+
"step": 1510
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 24.32,
|
| 1207 |
+
"learning_rate": 2.031063321385902e-05,
|
| 1208 |
+
"loss": 1.2116,
|
| 1209 |
+
"step": 1520
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 24.48,
|
| 1213 |
+
"learning_rate": 1.9713261648745522e-05,
|
| 1214 |
+
"loss": 1.2061,
|
| 1215 |
+
"step": 1530
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 24.64,
|
| 1219 |
+
"learning_rate": 1.9115890083632022e-05,
|
| 1220 |
+
"loss": 1.2072,
|
| 1221 |
+
"step": 1540
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 24.8,
|
| 1225 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1226 |
+
"loss": 1.2144,
|
| 1227 |
+
"step": 1550
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 24.96,
|
| 1231 |
+
"learning_rate": 1.7921146953405018e-05,
|
| 1232 |
+
"loss": 1.2442,
|
| 1233 |
+
"step": 1560
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 24.99,
|
| 1237 |
+
"eval_accuracy": 0.5913190529875987,
|
| 1238 |
+
"eval_f1": 0.5672449138626566,
|
| 1239 |
+
"eval_loss": 1.1695806980133057,
|
| 1240 |
+
"eval_precision": 0.6061531146445093,
|
| 1241 |
+
"eval_recall": 0.5913190529875987,
|
| 1242 |
+
"eval_runtime": 21.8809,
|
| 1243 |
+
"eval_samples_per_second": 81.075,
|
| 1244 |
+
"eval_steps_per_second": 1.28,
|
| 1245 |
+
"step": 1562
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 25.12,
|
| 1249 |
+
"learning_rate": 1.7323775388291518e-05,
|
| 1250 |
+
"loss": 1.2032,
|
| 1251 |
+
"step": 1570
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 25.28,
|
| 1255 |
+
"learning_rate": 1.6726403823178017e-05,
|
| 1256 |
+
"loss": 1.22,
|
| 1257 |
+
"step": 1580
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 25.44,
|
| 1261 |
+
"learning_rate": 1.6129032258064517e-05,
|
| 1262 |
+
"loss": 1.2206,
|
| 1263 |
+
"step": 1590
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 25.6,
|
| 1267 |
+
"learning_rate": 1.5531660692951016e-05,
|
| 1268 |
+
"loss": 1.2222,
|
| 1269 |
+
"step": 1600
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 25.76,
|
| 1273 |
+
"learning_rate": 1.4934289127837516e-05,
|
| 1274 |
+
"loss": 1.2218,
|
| 1275 |
+
"step": 1610
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 25.92,
|
| 1279 |
+
"learning_rate": 1.4336917562724014e-05,
|
| 1280 |
+
"loss": 1.1913,
|
| 1281 |
+
"step": 1620
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 26.0,
|
| 1285 |
+
"eval_accuracy": 0.5918827508455468,
|
| 1286 |
+
"eval_f1": 0.5677595343942556,
|
| 1287 |
+
"eval_loss": 1.166059970855713,
|
| 1288 |
+
"eval_precision": 0.6011740510143309,
|
| 1289 |
+
"eval_recall": 0.5918827508455468,
|
| 1290 |
+
"eval_runtime": 24.7186,
|
| 1291 |
+
"eval_samples_per_second": 71.768,
|
| 1292 |
+
"eval_steps_per_second": 1.133,
|
| 1293 |
+
"step": 1625
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 26.08,
|
| 1297 |
+
"learning_rate": 1.3739545997610515e-05,
|
| 1298 |
+
"loss": 1.2119,
|
| 1299 |
+
"step": 1630
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 26.24,
|
| 1303 |
+
"learning_rate": 1.3142174432497015e-05,
|
| 1304 |
+
"loss": 1.2229,
|
| 1305 |
+
"step": 1640
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 26.4,
|
| 1309 |
+
"learning_rate": 1.2544802867383513e-05,
|
| 1310 |
+
"loss": 1.2139,
|
| 1311 |
+
"step": 1650
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 26.56,
|
| 1315 |
+
"learning_rate": 1.1947431302270013e-05,
|
| 1316 |
+
"loss": 1.228,
|
| 1317 |
+
"step": 1660
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 26.72,
|
| 1321 |
+
"learning_rate": 1.135005973715651e-05,
|
| 1322 |
+
"loss": 1.2139,
|
| 1323 |
+
"step": 1670
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 26.88,
|
| 1327 |
+
"learning_rate": 1.0752688172043012e-05,
|
| 1328 |
+
"loss": 1.2111,
|
| 1329 |
+
"step": 1680
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 26.99,
|
| 1333 |
+
"eval_accuracy": 0.5941375422773394,
|
| 1334 |
+
"eval_f1": 0.5702300711030653,
|
| 1335 |
+
"eval_loss": 1.1638890504837036,
|
| 1336 |
+
"eval_precision": 0.6024395376181177,
|
| 1337 |
+
"eval_recall": 0.5941375422773394,
|
| 1338 |
+
"eval_runtime": 21.6884,
|
| 1339 |
+
"eval_samples_per_second": 81.795,
|
| 1340 |
+
"eval_steps_per_second": 1.291,
|
| 1341 |
+
"step": 1687
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 27.04,
|
| 1345 |
+
"learning_rate": 1.015531660692951e-05,
|
| 1346 |
+
"loss": 1.2022,
|
| 1347 |
+
"step": 1690
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 27.2,
|
| 1351 |
+
"learning_rate": 9.557945041816011e-06,
|
| 1352 |
+
"loss": 1.2367,
|
| 1353 |
+
"step": 1700
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 27.36,
|
| 1357 |
+
"learning_rate": 8.960573476702509e-06,
|
| 1358 |
+
"loss": 1.2098,
|
| 1359 |
+
"step": 1710
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 27.52,
|
| 1363 |
+
"learning_rate": 8.363201911589009e-06,
|
| 1364 |
+
"loss": 1.2068,
|
| 1365 |
+
"step": 1720
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 27.68,
|
| 1369 |
+
"learning_rate": 7.765830346475508e-06,
|
| 1370 |
+
"loss": 1.2094,
|
| 1371 |
+
"step": 1730
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 27.84,
|
| 1375 |
+
"learning_rate": 7.168458781362007e-06,
|
| 1376 |
+
"loss": 1.2081,
|
| 1377 |
+
"step": 1740
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 28.0,
|
| 1381 |
+
"learning_rate": 6.5710872162485075e-06,
|
| 1382 |
+
"loss": 1.2168,
|
| 1383 |
+
"step": 1750
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 28.0,
|
| 1387 |
+
"eval_accuracy": 0.5952649379932357,
|
| 1388 |
+
"eval_f1": 0.5714376467349129,
|
| 1389 |
+
"eval_loss": 1.1634987592697144,
|
| 1390 |
+
"eval_precision": 0.6038590156410394,
|
| 1391 |
+
"eval_recall": 0.5952649379932357,
|
| 1392 |
+
"eval_runtime": 21.7656,
|
| 1393 |
+
"eval_samples_per_second": 81.505,
|
| 1394 |
+
"eval_steps_per_second": 1.286,
|
| 1395 |
+
"step": 1750
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 28.16,
|
| 1399 |
+
"learning_rate": 5.973715651135006e-06,
|
| 1400 |
+
"loss": 1.2345,
|
| 1401 |
+
"step": 1760
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 28.32,
|
| 1405 |
+
"learning_rate": 5.376344086021506e-06,
|
| 1406 |
+
"loss": 1.2111,
|
| 1407 |
+
"step": 1770
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 28.48,
|
| 1411 |
+
"learning_rate": 4.7789725209080055e-06,
|
| 1412 |
+
"loss": 1.2238,
|
| 1413 |
+
"step": 1780
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 28.64,
|
| 1417 |
+
"learning_rate": 4.181600955794504e-06,
|
| 1418 |
+
"loss": 1.1954,
|
| 1419 |
+
"step": 1790
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 28.8,
|
| 1423 |
+
"learning_rate": 3.5842293906810035e-06,
|
| 1424 |
+
"loss": 1.2056,
|
| 1425 |
+
"step": 1800
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 28.96,
|
| 1429 |
+
"learning_rate": 2.986857825567503e-06,
|
| 1430 |
+
"loss": 1.2114,
|
| 1431 |
+
"step": 1810
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 28.99,
|
| 1435 |
+
"eval_accuracy": 0.5947012401352875,
|
| 1436 |
+
"eval_f1": 0.5708424800157854,
|
| 1437 |
+
"eval_loss": 1.1630581617355347,
|
| 1438 |
+
"eval_precision": 0.6033834911301407,
|
| 1439 |
+
"eval_recall": 0.5947012401352875,
|
| 1440 |
+
"eval_runtime": 21.8632,
|
| 1441 |
+
"eval_samples_per_second": 81.141,
|
| 1442 |
+
"eval_steps_per_second": 1.281,
|
| 1443 |
+
"step": 1812
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 29.12,
|
| 1447 |
+
"learning_rate": 2.3894862604540028e-06,
|
| 1448 |
+
"loss": 1.2062,
|
| 1449 |
+
"step": 1820
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 29.28,
|
| 1453 |
+
"learning_rate": 1.7921146953405017e-06,
|
| 1454 |
+
"loss": 1.2096,
|
| 1455 |
+
"step": 1830
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 29.44,
|
| 1459 |
+
"learning_rate": 1.1947431302270014e-06,
|
| 1460 |
+
"loss": 1.195,
|
| 1461 |
+
"step": 1840
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 29.6,
|
| 1465 |
+
"learning_rate": 5.973715651135007e-07,
|
| 1466 |
+
"loss": 1.2149,
|
| 1467 |
+
"step": 1850
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 29.76,
|
| 1471 |
+
"learning_rate": 0.0,
|
| 1472 |
+
"loss": 1.242,
|
| 1473 |
+
"step": 1860
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 29.76,
|
| 1477 |
+
"eval_accuracy": 0.5941375422773394,
|
| 1478 |
+
"eval_f1": 0.5702626157511408,
|
| 1479 |
+
"eval_loss": 1.16298246383667,
|
| 1480 |
+
"eval_precision": 0.6025735728226277,
|
| 1481 |
+
"eval_recall": 0.5941375422773394,
|
| 1482 |
+
"eval_runtime": 21.8833,
|
| 1483 |
+
"eval_samples_per_second": 81.066,
|
| 1484 |
+
"eval_steps_per_second": 1.28,
|
| 1485 |
+
"step": 1860
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 29.76,
|
| 1489 |
+
"step": 1860,
|
| 1490 |
+
"total_flos": 1.0940057452591763e+20,
|
| 1491 |
+
"train_loss": 1.3704575569398942,
|
| 1492 |
+
"train_runtime": 8385.7458,
|
| 1493 |
+
"train_samples_per_second": 57.104,
|
| 1494 |
+
"train_steps_per_second": 0.222
|
| 1495 |
+
}
|
| 1496 |
+
],
|
| 1497 |
+
"logging_steps": 10,
|
| 1498 |
+
"max_steps": 1860,
|
| 1499 |
+
"num_input_tokens_seen": 0,
|
| 1500 |
+
"num_train_epochs": 30,
|
| 1501 |
+
"save_steps": 500,
|
| 1502 |
+
"total_flos": 1.0940057452591763e+20,
|
| 1503 |
+
"train_batch_size": 64,
|
| 1504 |
+
"trial_name": null,
|
| 1505 |
+
"trial_params": null
|
| 1506 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1ad4e694ae30159860a2ce22530b0bf3e812fe826a5ba3bca685868e02e3575
|
| 3 |
+
size 4920
|