Upload folder using huggingface_hub
Browse files- config.json +135 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +23 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +528 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,135 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cvt-32x8-7seg-scoreboard-digit",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CvtForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_drop_rate": [
|
| 7 |
+
0.0,
|
| 8 |
+
0.0,
|
| 9 |
+
0.0
|
| 10 |
+
],
|
| 11 |
+
"cls_token": [
|
| 12 |
+
false,
|
| 13 |
+
false,
|
| 14 |
+
true
|
| 15 |
+
],
|
| 16 |
+
"depth": [
|
| 17 |
+
1,
|
| 18 |
+
2,
|
| 19 |
+
10
|
| 20 |
+
],
|
| 21 |
+
"drop_path_rate": [
|
| 22 |
+
0.0,
|
| 23 |
+
0.0,
|
| 24 |
+
0.1
|
| 25 |
+
],
|
| 26 |
+
"drop_rate": [
|
| 27 |
+
0.0,
|
| 28 |
+
0.0,
|
| 29 |
+
0.0
|
| 30 |
+
],
|
| 31 |
+
"embed_dim": [
|
| 32 |
+
64,
|
| 33 |
+
192,
|
| 34 |
+
384
|
| 35 |
+
],
|
| 36 |
+
"id2label": {
|
| 37 |
+
"0": "0",
|
| 38 |
+
"1": "1",
|
| 39 |
+
"10": " ",
|
| 40 |
+
"2": "2",
|
| 41 |
+
"3": "3",
|
| 42 |
+
"4": "4",
|
| 43 |
+
"5": "5",
|
| 44 |
+
"6": "6",
|
| 45 |
+
"7": "7",
|
| 46 |
+
"8": "8",
|
| 47 |
+
"9": "9"
|
| 48 |
+
},
|
| 49 |
+
"image_size": 224,
|
| 50 |
+
"initializer_range": 0.02,
|
| 51 |
+
"kernel_qkv": [
|
| 52 |
+
3,
|
| 53 |
+
3,
|
| 54 |
+
3
|
| 55 |
+
],
|
| 56 |
+
"label2id": {
|
| 57 |
+
" ": "10",
|
| 58 |
+
"0": "0",
|
| 59 |
+
"1": "1",
|
| 60 |
+
"2": "2",
|
| 61 |
+
"3": "3",
|
| 62 |
+
"4": "4",
|
| 63 |
+
"5": "5",
|
| 64 |
+
"6": "6",
|
| 65 |
+
"7": "7",
|
| 66 |
+
"8": "8",
|
| 67 |
+
"9": "9"
|
| 68 |
+
},
|
| 69 |
+
"layer_norm_eps": 1e-12,
|
| 70 |
+
"mlp_ratio": [
|
| 71 |
+
4.0,
|
| 72 |
+
4.0,
|
| 73 |
+
4.0
|
| 74 |
+
],
|
| 75 |
+
"model_type": "cvt",
|
| 76 |
+
"num_channels": 3,
|
| 77 |
+
"num_heads": [
|
| 78 |
+
1,
|
| 79 |
+
3,
|
| 80 |
+
6
|
| 81 |
+
],
|
| 82 |
+
"num_stages": 3,
|
| 83 |
+
"padding_kv": [
|
| 84 |
+
1,
|
| 85 |
+
1,
|
| 86 |
+
1
|
| 87 |
+
],
|
| 88 |
+
"padding_q": [
|
| 89 |
+
1,
|
| 90 |
+
1,
|
| 91 |
+
1
|
| 92 |
+
],
|
| 93 |
+
"patch_padding": [
|
| 94 |
+
2,
|
| 95 |
+
1,
|
| 96 |
+
1
|
| 97 |
+
],
|
| 98 |
+
"patch_sizes": [
|
| 99 |
+
7,
|
| 100 |
+
3,
|
| 101 |
+
3
|
| 102 |
+
],
|
| 103 |
+
"patch_stride": [
|
| 104 |
+
4,
|
| 105 |
+
2,
|
| 106 |
+
2
|
| 107 |
+
],
|
| 108 |
+
"pos_embed": [
|
| 109 |
+
false,
|
| 110 |
+
false,
|
| 111 |
+
false
|
| 112 |
+
],
|
| 113 |
+
"qkv_bias": [
|
| 114 |
+
true,
|
| 115 |
+
true,
|
| 116 |
+
true
|
| 117 |
+
],
|
| 118 |
+
"qkv_projection_method": [
|
| 119 |
+
"dw_bn",
|
| 120 |
+
"dw_bn",
|
| 121 |
+
"dw_bn"
|
| 122 |
+
],
|
| 123 |
+
"stride_kv": [
|
| 124 |
+
2,
|
| 125 |
+
2,
|
| 126 |
+
2
|
| 127 |
+
],
|
| 128 |
+
"stride_q": [
|
| 129 |
+
1,
|
| 130 |
+
1,
|
| 131 |
+
1
|
| 132 |
+
],
|
| 133 |
+
"torch_dtype": "float32",
|
| 134 |
+
"transformers_version": "4.37.0.dev0"
|
| 135 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1caae663141e4fa2a48ee98e11d7a2da599320e29ccf5851127297ab79690f49
|
| 3 |
+
size 78643452
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b90e83ed6b8c58fbd29ea2e368e707ad78f94ad1617fffea71b4682c1f04980e
|
| 3 |
+
size 157219604
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_pct": 0.875,
|
| 3 |
+
"do_normalize": false,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": false,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.485,
|
| 8 |
+
0.456,
|
| 9 |
+
0.406
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ConvNextImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.229,
|
| 14 |
+
0.224,
|
| 15 |
+
0.225
|
| 16 |
+
],
|
| 17 |
+
"resample": 3,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 32,
|
| 21 |
+
"width": 8
|
| 22 |
+
}
|
| 23 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:979206eafe5145ff0c9edd665fed37edf7d4971fb09007a6eb59d5aae1b27c92
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6441d395baa308580422451a832e8a63c98eac6cbcb34556e599dc30265dd82a
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,528 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.06640350073575974,
|
| 3 |
+
"best_model_checkpoint": "clock_output_cvt/checkpoint-475",
|
| 4 |
+
"epoch": 24.675324675324674,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 475,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.52,
|
| 13 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 14 |
+
"loss": 2.4077,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.99,
|
| 19 |
+
"eval_accuracy": 0.03625954198473282,
|
| 20 |
+
"eval_loss": 2.3564352989196777,
|
| 21 |
+
"eval_runtime": 0.6407,
|
| 22 |
+
"eval_samples_per_second": 817.896,
|
| 23 |
+
"eval_steps_per_second": 51.509,
|
| 24 |
+
"step": 19
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.04,
|
| 28 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 29 |
+
"loss": 2.388,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 1.56,
|
| 34 |
+
"learning_rate": 3.125e-05,
|
| 35 |
+
"loss": 2.3477,
|
| 36 |
+
"step": 30
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 1.97,
|
| 40 |
+
"eval_accuracy": 0.4122137404580153,
|
| 41 |
+
"eval_loss": 2.189662218093872,
|
| 42 |
+
"eval_runtime": 0.6085,
|
| 43 |
+
"eval_samples_per_second": 861.15,
|
| 44 |
+
"eval_steps_per_second": 54.233,
|
| 45 |
+
"step": 38
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.08,
|
| 49 |
+
"learning_rate": 4.166666666666667e-05,
|
| 50 |
+
"loss": 2.2977,
|
| 51 |
+
"step": 40
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.6,
|
| 55 |
+
"learning_rate": 4.9765807962529274e-05,
|
| 56 |
+
"loss": 2.1449,
|
| 57 |
+
"step": 50
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.96,
|
| 61 |
+
"eval_accuracy": 0.816793893129771,
|
| 62 |
+
"eval_loss": 1.8227535486221313,
|
| 63 |
+
"eval_runtime": 0.613,
|
| 64 |
+
"eval_samples_per_second": 854.76,
|
| 65 |
+
"eval_steps_per_second": 53.83,
|
| 66 |
+
"step": 57
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 3.12,
|
| 70 |
+
"learning_rate": 4.8594847775175645e-05,
|
| 71 |
+
"loss": 2.0451,
|
| 72 |
+
"step": 60
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 3.64,
|
| 76 |
+
"learning_rate": 4.742388758782202e-05,
|
| 77 |
+
"loss": 1.7728,
|
| 78 |
+
"step": 70
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 4.0,
|
| 82 |
+
"eval_accuracy": 0.8549618320610687,
|
| 83 |
+
"eval_loss": 1.2455334663391113,
|
| 84 |
+
"eval_runtime": 0.6145,
|
| 85 |
+
"eval_samples_per_second": 852.784,
|
| 86 |
+
"eval_steps_per_second": 53.706,
|
| 87 |
+
"step": 77
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 4.16,
|
| 91 |
+
"learning_rate": 4.625292740046839e-05,
|
| 92 |
+
"loss": 1.5092,
|
| 93 |
+
"step": 80
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 4.68,
|
| 97 |
+
"learning_rate": 4.508196721311476e-05,
|
| 98 |
+
"loss": 1.3611,
|
| 99 |
+
"step": 90
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 4.99,
|
| 103 |
+
"eval_accuracy": 0.9408396946564885,
|
| 104 |
+
"eval_loss": 0.8229649662971497,
|
| 105 |
+
"eval_runtime": 0.7007,
|
| 106 |
+
"eval_samples_per_second": 747.777,
|
| 107 |
+
"eval_steps_per_second": 47.093,
|
| 108 |
+
"step": 96
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 5.19,
|
| 112 |
+
"learning_rate": 4.3911007025761124e-05,
|
| 113 |
+
"loss": 1.254,
|
| 114 |
+
"step": 100
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 5.71,
|
| 118 |
+
"learning_rate": 4.2740046838407495e-05,
|
| 119 |
+
"loss": 1.1696,
|
| 120 |
+
"step": 110
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 5.97,
|
| 124 |
+
"eval_accuracy": 0.9580152671755725,
|
| 125 |
+
"eval_loss": 0.6116180419921875,
|
| 126 |
+
"eval_runtime": 0.6501,
|
| 127 |
+
"eval_samples_per_second": 806.052,
|
| 128 |
+
"eval_steps_per_second": 50.763,
|
| 129 |
+
"step": 115
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 6.23,
|
| 133 |
+
"learning_rate": 4.156908665105387e-05,
|
| 134 |
+
"loss": 1.0323,
|
| 135 |
+
"step": 120
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 6.75,
|
| 139 |
+
"learning_rate": 4.039812646370024e-05,
|
| 140 |
+
"loss": 1.0261,
|
| 141 |
+
"step": 130
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 6.96,
|
| 145 |
+
"eval_accuracy": 0.9866412213740458,
|
| 146 |
+
"eval_loss": 0.4360557198524475,
|
| 147 |
+
"eval_runtime": 0.6176,
|
| 148 |
+
"eval_samples_per_second": 848.435,
|
| 149 |
+
"eval_steps_per_second": 53.432,
|
| 150 |
+
"step": 134
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 7.27,
|
| 154 |
+
"learning_rate": 3.92271662763466e-05,
|
| 155 |
+
"loss": 0.7872,
|
| 156 |
+
"step": 140
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 7.79,
|
| 160 |
+
"learning_rate": 3.8056206088992974e-05,
|
| 161 |
+
"loss": 0.8913,
|
| 162 |
+
"step": 150
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 8.0,
|
| 166 |
+
"eval_accuracy": 0.9790076335877863,
|
| 167 |
+
"eval_loss": 0.3085819184780121,
|
| 168 |
+
"eval_runtime": 0.6116,
|
| 169 |
+
"eval_samples_per_second": 856.814,
|
| 170 |
+
"eval_steps_per_second": 53.96,
|
| 171 |
+
"step": 154
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 8.31,
|
| 175 |
+
"learning_rate": 3.6885245901639346e-05,
|
| 176 |
+
"loss": 0.7895,
|
| 177 |
+
"step": 160
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 8.83,
|
| 181 |
+
"learning_rate": 3.571428571428572e-05,
|
| 182 |
+
"loss": 0.6873,
|
| 183 |
+
"step": 170
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 8.99,
|
| 187 |
+
"eval_accuracy": 0.9904580152671756,
|
| 188 |
+
"eval_loss": 0.21129438281059265,
|
| 189 |
+
"eval_runtime": 0.6415,
|
| 190 |
+
"eval_samples_per_second": 816.831,
|
| 191 |
+
"eval_steps_per_second": 51.442,
|
| 192 |
+
"step": 173
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 9.35,
|
| 196 |
+
"learning_rate": 3.454332552693209e-05,
|
| 197 |
+
"loss": 0.6743,
|
| 198 |
+
"step": 180
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 9.87,
|
| 202 |
+
"learning_rate": 3.337236533957845e-05,
|
| 203 |
+
"loss": 0.7179,
|
| 204 |
+
"step": 190
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 9.97,
|
| 208 |
+
"eval_accuracy": 0.9904580152671756,
|
| 209 |
+
"eval_loss": 0.18043160438537598,
|
| 210 |
+
"eval_runtime": 0.6319,
|
| 211 |
+
"eval_samples_per_second": 829.26,
|
| 212 |
+
"eval_steps_per_second": 52.224,
|
| 213 |
+
"step": 192
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 10.39,
|
| 217 |
+
"learning_rate": 3.220140515222483e-05,
|
| 218 |
+
"loss": 0.7141,
|
| 219 |
+
"step": 200
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 10.91,
|
| 223 |
+
"learning_rate": 3.1030444964871196e-05,
|
| 224 |
+
"loss": 0.6876,
|
| 225 |
+
"step": 210
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 10.96,
|
| 229 |
+
"eval_accuracy": 0.9923664122137404,
|
| 230 |
+
"eval_loss": 0.14928863942623138,
|
| 231 |
+
"eval_runtime": 0.6689,
|
| 232 |
+
"eval_samples_per_second": 783.382,
|
| 233 |
+
"eval_steps_per_second": 49.335,
|
| 234 |
+
"step": 211
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 11.43,
|
| 238 |
+
"learning_rate": 2.9859484777517567e-05,
|
| 239 |
+
"loss": 0.5847,
|
| 240 |
+
"step": 220
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 11.95,
|
| 244 |
+
"learning_rate": 2.8688524590163935e-05,
|
| 245 |
+
"loss": 0.5725,
|
| 246 |
+
"step": 230
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 12.0,
|
| 250 |
+
"eval_accuracy": 0.9923664122137404,
|
| 251 |
+
"eval_loss": 0.12330139428377151,
|
| 252 |
+
"eval_runtime": 0.6335,
|
| 253 |
+
"eval_samples_per_second": 827.089,
|
| 254 |
+
"eval_steps_per_second": 52.088,
|
| 255 |
+
"step": 231
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 12.47,
|
| 259 |
+
"learning_rate": 2.7517564402810303e-05,
|
| 260 |
+
"loss": 0.6264,
|
| 261 |
+
"step": 240
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 12.99,
|
| 265 |
+
"learning_rate": 2.6346604215456678e-05,
|
| 266 |
+
"loss": 0.6068,
|
| 267 |
+
"step": 250
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 12.99,
|
| 271 |
+
"eval_accuracy": 0.9923664122137404,
|
| 272 |
+
"eval_loss": 0.10889697074890137,
|
| 273 |
+
"eval_runtime": 0.6123,
|
| 274 |
+
"eval_samples_per_second": 855.795,
|
| 275 |
+
"eval_steps_per_second": 53.895,
|
| 276 |
+
"step": 250
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 13.51,
|
| 280 |
+
"learning_rate": 2.5175644028103046e-05,
|
| 281 |
+
"loss": 0.7263,
|
| 282 |
+
"step": 260
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 13.97,
|
| 286 |
+
"eval_accuracy": 0.9923664122137404,
|
| 287 |
+
"eval_loss": 0.09741852432489395,
|
| 288 |
+
"eval_runtime": 0.6166,
|
| 289 |
+
"eval_samples_per_second": 849.786,
|
| 290 |
+
"eval_steps_per_second": 53.517,
|
| 291 |
+
"step": 269
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 14.03,
|
| 295 |
+
"learning_rate": 2.4004683840749414e-05,
|
| 296 |
+
"loss": 0.5785,
|
| 297 |
+
"step": 270
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 14.55,
|
| 301 |
+
"learning_rate": 2.2833723653395785e-05,
|
| 302 |
+
"loss": 0.5596,
|
| 303 |
+
"step": 280
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 14.96,
|
| 307 |
+
"eval_accuracy": 0.9923664122137404,
|
| 308 |
+
"eval_loss": 0.08803129196166992,
|
| 309 |
+
"eval_runtime": 0.6127,
|
| 310 |
+
"eval_samples_per_second": 855.286,
|
| 311 |
+
"eval_steps_per_second": 53.863,
|
| 312 |
+
"step": 288
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 15.06,
|
| 316 |
+
"learning_rate": 2.1662763466042153e-05,
|
| 317 |
+
"loss": 0.604,
|
| 318 |
+
"step": 290
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 15.58,
|
| 322 |
+
"learning_rate": 2.0491803278688525e-05,
|
| 323 |
+
"loss": 0.5638,
|
| 324 |
+
"step": 300
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 16.0,
|
| 328 |
+
"eval_accuracy": 0.9923664122137404,
|
| 329 |
+
"eval_loss": 0.08413369953632355,
|
| 330 |
+
"eval_runtime": 0.6464,
|
| 331 |
+
"eval_samples_per_second": 810.624,
|
| 332 |
+
"eval_steps_per_second": 51.051,
|
| 333 |
+
"step": 308
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 16.1,
|
| 337 |
+
"learning_rate": 1.9320843091334896e-05,
|
| 338 |
+
"loss": 0.5579,
|
| 339 |
+
"step": 310
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 16.62,
|
| 343 |
+
"learning_rate": 1.8149882903981267e-05,
|
| 344 |
+
"loss": 0.5601,
|
| 345 |
+
"step": 320
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 16.99,
|
| 349 |
+
"eval_accuracy": 0.9923664122137404,
|
| 350 |
+
"eval_loss": 0.07752922177314758,
|
| 351 |
+
"eval_runtime": 0.6764,
|
| 352 |
+
"eval_samples_per_second": 774.698,
|
| 353 |
+
"eval_steps_per_second": 48.788,
|
| 354 |
+
"step": 327
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 17.14,
|
| 358 |
+
"learning_rate": 1.6978922716627635e-05,
|
| 359 |
+
"loss": 0.3986,
|
| 360 |
+
"step": 330
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 17.66,
|
| 364 |
+
"learning_rate": 1.5807962529274007e-05,
|
| 365 |
+
"loss": 0.606,
|
| 366 |
+
"step": 340
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 17.97,
|
| 370 |
+
"eval_accuracy": 0.9923664122137404,
|
| 371 |
+
"eval_loss": 0.07416040450334549,
|
| 372 |
+
"eval_runtime": 0.6307,
|
| 373 |
+
"eval_samples_per_second": 830.823,
|
| 374 |
+
"eval_steps_per_second": 52.323,
|
| 375 |
+
"step": 346
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 18.18,
|
| 379 |
+
"learning_rate": 1.4637002341920375e-05,
|
| 380 |
+
"loss": 0.6279,
|
| 381 |
+
"step": 350
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 18.7,
|
| 385 |
+
"learning_rate": 1.3466042154566746e-05,
|
| 386 |
+
"loss": 0.5748,
|
| 387 |
+
"step": 360
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 18.96,
|
| 391 |
+
"eval_accuracy": 0.9923664122137404,
|
| 392 |
+
"eval_loss": 0.07282942533493042,
|
| 393 |
+
"eval_runtime": 0.8001,
|
| 394 |
+
"eval_samples_per_second": 654.911,
|
| 395 |
+
"eval_steps_per_second": 41.244,
|
| 396 |
+
"step": 365
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 19.22,
|
| 400 |
+
"learning_rate": 1.2295081967213116e-05,
|
| 401 |
+
"loss": 0.5834,
|
| 402 |
+
"step": 370
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 19.74,
|
| 406 |
+
"learning_rate": 1.1124121779859485e-05,
|
| 407 |
+
"loss": 0.4852,
|
| 408 |
+
"step": 380
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 20.0,
|
| 412 |
+
"eval_accuracy": 0.9923664122137404,
|
| 413 |
+
"eval_loss": 0.07014743238687515,
|
| 414 |
+
"eval_runtime": 0.7282,
|
| 415 |
+
"eval_samples_per_second": 719.555,
|
| 416 |
+
"eval_steps_per_second": 45.315,
|
| 417 |
+
"step": 385
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 20.26,
|
| 421 |
+
"learning_rate": 9.953161592505855e-06,
|
| 422 |
+
"loss": 0.5781,
|
| 423 |
+
"step": 390
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 20.78,
|
| 427 |
+
"learning_rate": 8.782201405152225e-06,
|
| 428 |
+
"loss": 0.4564,
|
| 429 |
+
"step": 400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 20.99,
|
| 433 |
+
"eval_accuracy": 0.9923664122137404,
|
| 434 |
+
"eval_loss": 0.06891454756259918,
|
| 435 |
+
"eval_runtime": 0.7574,
|
| 436 |
+
"eval_samples_per_second": 691.858,
|
| 437 |
+
"eval_steps_per_second": 43.571,
|
| 438 |
+
"step": 404
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 21.3,
|
| 442 |
+
"learning_rate": 7.611241217798595e-06,
|
| 443 |
+
"loss": 0.5382,
|
| 444 |
+
"step": 410
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 21.82,
|
| 448 |
+
"learning_rate": 6.440281030444965e-06,
|
| 449 |
+
"loss": 0.4278,
|
| 450 |
+
"step": 420
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 21.97,
|
| 454 |
+
"eval_accuracy": 0.9923664122137404,
|
| 455 |
+
"eval_loss": 0.06956692785024643,
|
| 456 |
+
"eval_runtime": 0.7478,
|
| 457 |
+
"eval_samples_per_second": 700.728,
|
| 458 |
+
"eval_steps_per_second": 44.13,
|
| 459 |
+
"step": 423
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 22.34,
|
| 463 |
+
"learning_rate": 5.2693208430913356e-06,
|
| 464 |
+
"loss": 0.4226,
|
| 465 |
+
"step": 430
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 22.86,
|
| 469 |
+
"learning_rate": 4.098360655737704e-06,
|
| 470 |
+
"loss": 0.481,
|
| 471 |
+
"step": 440
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 22.96,
|
| 475 |
+
"eval_accuracy": 0.9923664122137404,
|
| 476 |
+
"eval_loss": 0.06689619272947311,
|
| 477 |
+
"eval_runtime": 0.7742,
|
| 478 |
+
"eval_samples_per_second": 676.868,
|
| 479 |
+
"eval_steps_per_second": 42.627,
|
| 480 |
+
"step": 442
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 23.38,
|
| 484 |
+
"learning_rate": 2.9274004683840754e-06,
|
| 485 |
+
"loss": 0.5381,
|
| 486 |
+
"step": 450
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 23.9,
|
| 490 |
+
"learning_rate": 1.7564402810304448e-06,
|
| 491 |
+
"loss": 0.4477,
|
| 492 |
+
"step": 460
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 24.0,
|
| 496 |
+
"eval_accuracy": 0.9923664122137404,
|
| 497 |
+
"eval_loss": 0.06719958037137985,
|
| 498 |
+
"eval_runtime": 0.6158,
|
| 499 |
+
"eval_samples_per_second": 850.91,
|
| 500 |
+
"eval_steps_per_second": 53.588,
|
| 501 |
+
"step": 462
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 24.42,
|
| 505 |
+
"learning_rate": 5.85480093676815e-07,
|
| 506 |
+
"loss": 0.598,
|
| 507 |
+
"step": 470
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 24.68,
|
| 511 |
+
"eval_accuracy": 0.9923664122137404,
|
| 512 |
+
"eval_loss": 0.06640350073575974,
|
| 513 |
+
"eval_runtime": 0.6103,
|
| 514 |
+
"eval_samples_per_second": 858.552,
|
| 515 |
+
"eval_steps_per_second": 54.069,
|
| 516 |
+
"step": 475
|
| 517 |
+
}
|
| 518 |
+
],
|
| 519 |
+
"logging_steps": 10,
|
| 520 |
+
"max_steps": 475,
|
| 521 |
+
"num_input_tokens_seen": 0,
|
| 522 |
+
"num_train_epochs": 25,
|
| 523 |
+
"save_steps": 500,
|
| 524 |
+
"total_flos": 2737124951961600.0,
|
| 525 |
+
"train_batch_size": 16,
|
| 526 |
+
"trial_name": null,
|
| 527 |
+
"trial_params": null
|
| 528 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2abaed8304fcb84cbfe8bbe9481de248ad63e9506b0fb225576220c6a0dd255c
|
| 3 |
+
size 4664
|