Upload folder using huggingface_hub
#1
by
ericvo
- opened
- config.json +104 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1276 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "$",
|
| 13 |
+
"1": "&",
|
| 14 |
+
"10": "8",
|
| 15 |
+
"11": "9",
|
| 16 |
+
"12": "@",
|
| 17 |
+
"13": "A",
|
| 18 |
+
"14": "B",
|
| 19 |
+
"15": "C",
|
| 20 |
+
"16": "D",
|
| 21 |
+
"17": "E",
|
| 22 |
+
"18": "F",
|
| 23 |
+
"19": "G",
|
| 24 |
+
"2": "0",
|
| 25 |
+
"20": "H",
|
| 26 |
+
"21": "I",
|
| 27 |
+
"22": "J",
|
| 28 |
+
"23": "K",
|
| 29 |
+
"24": "L",
|
| 30 |
+
"25": "M",
|
| 31 |
+
"26": "N",
|
| 32 |
+
"27": "P",
|
| 33 |
+
"28": "Q",
|
| 34 |
+
"29": "R",
|
| 35 |
+
"3": "1",
|
| 36 |
+
"30": "S",
|
| 37 |
+
"31": "T",
|
| 38 |
+
"32": "U",
|
| 39 |
+
"33": "V",
|
| 40 |
+
"34": "W",
|
| 41 |
+
"35": "X",
|
| 42 |
+
"36": "Y",
|
| 43 |
+
"37": "Z",
|
| 44 |
+
"4": "2",
|
| 45 |
+
"5": "3",
|
| 46 |
+
"6": "4",
|
| 47 |
+
"7": "5",
|
| 48 |
+
"8": "6",
|
| 49 |
+
"9": "7"
|
| 50 |
+
},
|
| 51 |
+
"image_size": 224,
|
| 52 |
+
"initializer_range": 0.02,
|
| 53 |
+
"intermediate_size": 3072,
|
| 54 |
+
"label2id": {
|
| 55 |
+
"$": "0",
|
| 56 |
+
"&": "1",
|
| 57 |
+
"0": "2",
|
| 58 |
+
"1": "3",
|
| 59 |
+
"2": "4",
|
| 60 |
+
"3": "5",
|
| 61 |
+
"4": "6",
|
| 62 |
+
"5": "7",
|
| 63 |
+
"6": "8",
|
| 64 |
+
"7": "9",
|
| 65 |
+
"8": "10",
|
| 66 |
+
"9": "11",
|
| 67 |
+
"@": "12",
|
| 68 |
+
"A": "13",
|
| 69 |
+
"B": "14",
|
| 70 |
+
"C": "15",
|
| 71 |
+
"D": "16",
|
| 72 |
+
"E": "17",
|
| 73 |
+
"F": "18",
|
| 74 |
+
"G": "19",
|
| 75 |
+
"H": "20",
|
| 76 |
+
"I": "21",
|
| 77 |
+
"J": "22",
|
| 78 |
+
"K": "23",
|
| 79 |
+
"L": "24",
|
| 80 |
+
"M": "25",
|
| 81 |
+
"N": "26",
|
| 82 |
+
"P": "27",
|
| 83 |
+
"Q": "28",
|
| 84 |
+
"R": "29",
|
| 85 |
+
"S": "30",
|
| 86 |
+
"T": "31",
|
| 87 |
+
"U": "32",
|
| 88 |
+
"V": "33",
|
| 89 |
+
"W": "34",
|
| 90 |
+
"X": "35",
|
| 91 |
+
"Y": "36",
|
| 92 |
+
"Z": "37"
|
| 93 |
+
},
|
| 94 |
+
"layer_norm_eps": 1e-12,
|
| 95 |
+
"model_type": "vit",
|
| 96 |
+
"num_attention_heads": 12,
|
| 97 |
+
"num_channels": 3,
|
| 98 |
+
"num_hidden_layers": 12,
|
| 99 |
+
"patch_size": 16,
|
| 100 |
+
"problem_type": "single_label_classification",
|
| 101 |
+
"qkv_bias": true,
|
| 102 |
+
"torch_dtype": "float32",
|
| 103 |
+
"transformers_version": "4.31.0"
|
| 104 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d82abf7a2d71346cb612147f70e5ce2a52077c8b25ce2fd916a03f850465e346
|
| 3 |
+
size 686740357
|
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 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTFeatureExtractor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b5cfe2c1d39549fd9ad6c3c13b2f320ea6107f5771aace71f4f23ebf70747a6
|
| 3 |
+
size 343379437
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39232056ccfd436c15019799b0234cbd01d2c42fe70cfc50400b13b6cae1832b
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:855c89b7f32eb731e9b96739f0342e3107e09b1ea38d6288849b304854c6b06a
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1276 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.16805602610111237,
|
| 3 |
+
"best_model_checkpoint": "./vit-handwritten-characters/checkpoint-8400",
|
| 4 |
+
"epoch": 2.952548330404218,
|
| 5 |
+
"global_step": 8400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 9.882835383714118e-05,
|
| 13 |
+
"loss": 2.6668,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"eval_accuracy": 0.7636050763605077,
|
| 19 |
+
"eval_loss": 1.8537834882736206,
|
| 20 |
+
"eval_runtime": 53.1177,
|
| 21 |
+
"eval_samples_per_second": 87.523,
|
| 22 |
+
"eval_steps_per_second": 2.749,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07,
|
| 27 |
+
"learning_rate": 9.765670767428236e-05,
|
| 28 |
+
"loss": 1.3385,
|
| 29 |
+
"step": 200
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.07,
|
| 33 |
+
"eval_accuracy": 0.8698644869864487,
|
| 34 |
+
"eval_loss": 1.0306403636932373,
|
| 35 |
+
"eval_runtime": 50.6679,
|
| 36 |
+
"eval_samples_per_second": 91.754,
|
| 37 |
+
"eval_steps_per_second": 2.882,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11,
|
| 42 |
+
"learning_rate": 9.648506151142355e-05,
|
| 43 |
+
"loss": 0.8372,
|
| 44 |
+
"step": 300
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11,
|
| 48 |
+
"eval_accuracy": 0.8657775865777586,
|
| 49 |
+
"eval_loss": 0.7356651425361633,
|
| 50 |
+
"eval_runtime": 51.2063,
|
| 51 |
+
"eval_samples_per_second": 90.79,
|
| 52 |
+
"eval_steps_per_second": 2.851,
|
| 53 |
+
"step": 300
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.14,
|
| 57 |
+
"learning_rate": 9.531341534856473e-05,
|
| 58 |
+
"loss": 0.5838,
|
| 59 |
+
"step": 400
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.14,
|
| 63 |
+
"eval_accuracy": 0.899118089911809,
|
| 64 |
+
"eval_loss": 0.5292066335678101,
|
| 65 |
+
"eval_runtime": 51.0683,
|
| 66 |
+
"eval_samples_per_second": 91.035,
|
| 67 |
+
"eval_steps_per_second": 2.859,
|
| 68 |
+
"step": 400
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.18,
|
| 72 |
+
"learning_rate": 9.414176918570592e-05,
|
| 73 |
+
"loss": 0.4572,
|
| 74 |
+
"step": 500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.18,
|
| 78 |
+
"eval_accuracy": 0.901699290169929,
|
| 79 |
+
"eval_loss": 0.4536021947860718,
|
| 80 |
+
"eval_runtime": 51.5623,
|
| 81 |
+
"eval_samples_per_second": 90.163,
|
| 82 |
+
"eval_steps_per_second": 2.832,
|
| 83 |
+
"step": 500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.21,
|
| 87 |
+
"learning_rate": 9.29701230228471e-05,
|
| 88 |
+
"loss": 0.3808,
|
| 89 |
+
"step": 600
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.21,
|
| 93 |
+
"eval_accuracy": 0.9141750914175092,
|
| 94 |
+
"eval_loss": 0.37226173281669617,
|
| 95 |
+
"eval_runtime": 51.6002,
|
| 96 |
+
"eval_samples_per_second": 90.097,
|
| 97 |
+
"eval_steps_per_second": 2.829,
|
| 98 |
+
"step": 600
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.25,
|
| 102 |
+
"learning_rate": 9.17984768599883e-05,
|
| 103 |
+
"loss": 0.393,
|
| 104 |
+
"step": 700
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.25,
|
| 108 |
+
"eval_accuracy": 0.899763389976339,
|
| 109 |
+
"eval_loss": 0.42711377143859863,
|
| 110 |
+
"eval_runtime": 53.3282,
|
| 111 |
+
"eval_samples_per_second": 87.177,
|
| 112 |
+
"eval_steps_per_second": 2.738,
|
| 113 |
+
"step": 700
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.28,
|
| 117 |
+
"learning_rate": 9.062683069712947e-05,
|
| 118 |
+
"loss": 0.3611,
|
| 119 |
+
"step": 800
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.28,
|
| 123 |
+
"eval_accuracy": 0.8793288879328888,
|
| 124 |
+
"eval_loss": 0.41316691040992737,
|
| 125 |
+
"eval_runtime": 52.5044,
|
| 126 |
+
"eval_samples_per_second": 88.545,
|
| 127 |
+
"eval_steps_per_second": 2.781,
|
| 128 |
+
"step": 800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.32,
|
| 132 |
+
"learning_rate": 8.945518453427065e-05,
|
| 133 |
+
"loss": 0.3436,
|
| 134 |
+
"step": 900
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.32,
|
| 138 |
+
"eval_accuracy": 0.9068616906861691,
|
| 139 |
+
"eval_loss": 0.34593629837036133,
|
| 140 |
+
"eval_runtime": 52.4712,
|
| 141 |
+
"eval_samples_per_second": 88.601,
|
| 142 |
+
"eval_steps_per_second": 2.782,
|
| 143 |
+
"step": 900
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.35,
|
| 147 |
+
"learning_rate": 8.828353837141183e-05,
|
| 148 |
+
"loss": 0.3147,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.35,
|
| 153 |
+
"eval_accuracy": 0.9135297913529792,
|
| 154 |
+
"eval_loss": 0.32545194029808044,
|
| 155 |
+
"eval_runtime": 55.2872,
|
| 156 |
+
"eval_samples_per_second": 84.088,
|
| 157 |
+
"eval_steps_per_second": 2.641,
|
| 158 |
+
"step": 1000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.39,
|
| 162 |
+
"learning_rate": 8.711189220855302e-05,
|
| 163 |
+
"loss": 0.2887,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.39,
|
| 168 |
+
"eval_accuracy": 0.9137448913744891,
|
| 169 |
+
"eval_loss": 0.3017228841781616,
|
| 170 |
+
"eval_runtime": 52.7469,
|
| 171 |
+
"eval_samples_per_second": 88.138,
|
| 172 |
+
"eval_steps_per_second": 2.768,
|
| 173 |
+
"step": 1100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.42,
|
| 177 |
+
"learning_rate": 8.59402460456942e-05,
|
| 178 |
+
"loss": 0.2768,
|
| 179 |
+
"step": 1200
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.42,
|
| 183 |
+
"eval_accuracy": 0.9130995913099591,
|
| 184 |
+
"eval_loss": 0.3049895465373993,
|
| 185 |
+
"eval_runtime": 52.9848,
|
| 186 |
+
"eval_samples_per_second": 87.742,
|
| 187 |
+
"eval_steps_per_second": 2.756,
|
| 188 |
+
"step": 1200
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.46,
|
| 192 |
+
"learning_rate": 8.476859988283538e-05,
|
| 193 |
+
"loss": 0.3113,
|
| 194 |
+
"step": 1300
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.46,
|
| 198 |
+
"eval_accuracy": 0.9167562916756292,
|
| 199 |
+
"eval_loss": 0.2875942885875702,
|
| 200 |
+
"eval_runtime": 54.7094,
|
| 201 |
+
"eval_samples_per_second": 84.976,
|
| 202 |
+
"eval_steps_per_second": 2.669,
|
| 203 |
+
"step": 1300
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.49,
|
| 207 |
+
"learning_rate": 8.359695371997657e-05,
|
| 208 |
+
"loss": 0.2607,
|
| 209 |
+
"step": 1400
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.49,
|
| 213 |
+
"eval_accuracy": 0.9098730909873091,
|
| 214 |
+
"eval_loss": 0.33047187328338623,
|
| 215 |
+
"eval_runtime": 55.3261,
|
| 216 |
+
"eval_samples_per_second": 84.029,
|
| 217 |
+
"eval_steps_per_second": 2.639,
|
| 218 |
+
"step": 1400
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.53,
|
| 222 |
+
"learning_rate": 8.242530755711776e-05,
|
| 223 |
+
"loss": 0.288,
|
| 224 |
+
"step": 1500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.53,
|
| 228 |
+
"eval_accuracy": 0.9098730909873091,
|
| 229 |
+
"eval_loss": 0.3238196074962616,
|
| 230 |
+
"eval_runtime": 53.2815,
|
| 231 |
+
"eval_samples_per_second": 87.254,
|
| 232 |
+
"eval_steps_per_second": 2.74,
|
| 233 |
+
"step": 1500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.56,
|
| 237 |
+
"learning_rate": 8.125366139425894e-05,
|
| 238 |
+
"loss": 0.311,
|
| 239 |
+
"step": 1600
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.56,
|
| 243 |
+
"eval_accuracy": 0.9128844912884492,
|
| 244 |
+
"eval_loss": 0.2932077944278717,
|
| 245 |
+
"eval_runtime": 54.1056,
|
| 246 |
+
"eval_samples_per_second": 85.925,
|
| 247 |
+
"eval_steps_per_second": 2.698,
|
| 248 |
+
"step": 1600
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.6,
|
| 252 |
+
"learning_rate": 8.008201523140012e-05,
|
| 253 |
+
"loss": 0.2702,
|
| 254 |
+
"step": 1700
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6,
|
| 258 |
+
"eval_accuracy": 0.9214884921488492,
|
| 259 |
+
"eval_loss": 0.281431645154953,
|
| 260 |
+
"eval_runtime": 55.0433,
|
| 261 |
+
"eval_samples_per_second": 84.461,
|
| 262 |
+
"eval_steps_per_second": 2.652,
|
| 263 |
+
"step": 1700
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.63,
|
| 267 |
+
"learning_rate": 7.89103690685413e-05,
|
| 268 |
+
"loss": 0.2476,
|
| 269 |
+
"step": 1800
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.63,
|
| 273 |
+
"eval_accuracy": 0.899118089911809,
|
| 274 |
+
"eval_loss": 0.29802632331848145,
|
| 275 |
+
"eval_runtime": 53.6155,
|
| 276 |
+
"eval_samples_per_second": 86.71,
|
| 277 |
+
"eval_steps_per_second": 2.723,
|
| 278 |
+
"step": 1800
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.67,
|
| 282 |
+
"learning_rate": 7.773872290568249e-05,
|
| 283 |
+
"loss": 0.2833,
|
| 284 |
+
"step": 1900
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.67,
|
| 288 |
+
"eval_accuracy": 0.9283716928371692,
|
| 289 |
+
"eval_loss": 0.2524644136428833,
|
| 290 |
+
"eval_runtime": 53.6383,
|
| 291 |
+
"eval_samples_per_second": 86.673,
|
| 292 |
+
"eval_steps_per_second": 2.722,
|
| 293 |
+
"step": 1900
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.7,
|
| 297 |
+
"learning_rate": 7.656707674282367e-05,
|
| 298 |
+
"loss": 0.2542,
|
| 299 |
+
"step": 2000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.7,
|
| 303 |
+
"eval_accuracy": 0.9247149924714992,
|
| 304 |
+
"eval_loss": 0.2760772705078125,
|
| 305 |
+
"eval_runtime": 53.5886,
|
| 306 |
+
"eval_samples_per_second": 86.753,
|
| 307 |
+
"eval_steps_per_second": 2.724,
|
| 308 |
+
"step": 2000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.74,
|
| 312 |
+
"learning_rate": 7.539543057996485e-05,
|
| 313 |
+
"loss": 0.2405,
|
| 314 |
+
"step": 2100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.74,
|
| 318 |
+
"eval_accuracy": 0.9229941922994193,
|
| 319 |
+
"eval_loss": 0.2586613595485687,
|
| 320 |
+
"eval_runtime": 55.7532,
|
| 321 |
+
"eval_samples_per_second": 83.385,
|
| 322 |
+
"eval_steps_per_second": 2.619,
|
| 323 |
+
"step": 2100
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.77,
|
| 327 |
+
"learning_rate": 7.422378441710603e-05,
|
| 328 |
+
"loss": 0.2404,
|
| 329 |
+
"step": 2200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.77,
|
| 333 |
+
"eval_accuracy": 0.9184770918477092,
|
| 334 |
+
"eval_loss": 0.25114524364471436,
|
| 335 |
+
"eval_runtime": 54.8709,
|
| 336 |
+
"eval_samples_per_second": 84.726,
|
| 337 |
+
"eval_steps_per_second": 2.661,
|
| 338 |
+
"step": 2200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.81,
|
| 342 |
+
"learning_rate": 7.305213825424722e-05,
|
| 343 |
+
"loss": 0.2277,
|
| 344 |
+
"step": 2300
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.81,
|
| 348 |
+
"eval_accuracy": 0.9191223919122392,
|
| 349 |
+
"eval_loss": 0.2526193857192993,
|
| 350 |
+
"eval_runtime": 54.7258,
|
| 351 |
+
"eval_samples_per_second": 84.951,
|
| 352 |
+
"eval_steps_per_second": 2.668,
|
| 353 |
+
"step": 2300
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.84,
|
| 357 |
+
"learning_rate": 7.188049209138841e-05,
|
| 358 |
+
"loss": 0.2399,
|
| 359 |
+
"step": 2400
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.84,
|
| 363 |
+
"eval_accuracy": 0.9214884921488492,
|
| 364 |
+
"eval_loss": 0.2550754249095917,
|
| 365 |
+
"eval_runtime": 55.744,
|
| 366 |
+
"eval_samples_per_second": 83.399,
|
| 367 |
+
"eval_steps_per_second": 2.619,
|
| 368 |
+
"step": 2400
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.88,
|
| 372 |
+
"learning_rate": 7.070884592852959e-05,
|
| 373 |
+
"loss": 0.2336,
|
| 374 |
+
"step": 2500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.88,
|
| 378 |
+
"eval_accuracy": 0.9219186921918692,
|
| 379 |
+
"eval_loss": 0.23437733948230743,
|
| 380 |
+
"eval_runtime": 53.9586,
|
| 381 |
+
"eval_samples_per_second": 86.159,
|
| 382 |
+
"eval_steps_per_second": 2.706,
|
| 383 |
+
"step": 2500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.91,
|
| 387 |
+
"learning_rate": 6.953719976567077e-05,
|
| 388 |
+
"loss": 0.2246,
|
| 389 |
+
"step": 2600
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.91,
|
| 393 |
+
"eval_accuracy": 0.9197676919767692,
|
| 394 |
+
"eval_loss": 0.24808667600154877,
|
| 395 |
+
"eval_runtime": 53.4909,
|
| 396 |
+
"eval_samples_per_second": 86.912,
|
| 397 |
+
"eval_steps_per_second": 2.729,
|
| 398 |
+
"step": 2600
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.95,
|
| 402 |
+
"learning_rate": 6.836555360281195e-05,
|
| 403 |
+
"loss": 0.2284,
|
| 404 |
+
"step": 2700
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.95,
|
| 408 |
+
"eval_accuracy": 0.9322434932243493,
|
| 409 |
+
"eval_loss": 0.21941034495830536,
|
| 410 |
+
"eval_runtime": 53.0587,
|
| 411 |
+
"eval_samples_per_second": 87.62,
|
| 412 |
+
"eval_steps_per_second": 2.752,
|
| 413 |
+
"step": 2700
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.98,
|
| 417 |
+
"learning_rate": 6.719390743995314e-05,
|
| 418 |
+
"loss": 0.2335,
|
| 419 |
+
"step": 2800
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.98,
|
| 423 |
+
"eval_accuracy": 0.9331038933103893,
|
| 424 |
+
"eval_loss": 0.2168220579624176,
|
| 425 |
+
"eval_runtime": 56.1589,
|
| 426 |
+
"eval_samples_per_second": 82.783,
|
| 427 |
+
"eval_steps_per_second": 2.6,
|
| 428 |
+
"step": 2800
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.02,
|
| 432 |
+
"learning_rate": 6.602226127709432e-05,
|
| 433 |
+
"loss": 0.1883,
|
| 434 |
+
"step": 2900
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.02,
|
| 438 |
+
"eval_accuracy": 0.9229941922994193,
|
| 439 |
+
"eval_loss": 0.24746185541152954,
|
| 440 |
+
"eval_runtime": 54.8887,
|
| 441 |
+
"eval_samples_per_second": 84.699,
|
| 442 |
+
"eval_steps_per_second": 2.66,
|
| 443 |
+
"step": 2900
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.05,
|
| 447 |
+
"learning_rate": 6.48506151142355e-05,
|
| 448 |
+
"loss": 0.194,
|
| 449 |
+
"step": 3000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.05,
|
| 453 |
+
"eval_accuracy": 0.9328887932888793,
|
| 454 |
+
"eval_loss": 0.2247306853532791,
|
| 455 |
+
"eval_runtime": 54.695,
|
| 456 |
+
"eval_samples_per_second": 84.999,
|
| 457 |
+
"eval_steps_per_second": 2.669,
|
| 458 |
+
"step": 3000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.09,
|
| 462 |
+
"learning_rate": 6.367896895137668e-05,
|
| 463 |
+
"loss": 0.2097,
|
| 464 |
+
"step": 3100
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.09,
|
| 468 |
+
"eval_accuracy": 0.9272961927296193,
|
| 469 |
+
"eval_loss": 0.21885570883750916,
|
| 470 |
+
"eval_runtime": 55.7057,
|
| 471 |
+
"eval_samples_per_second": 83.456,
|
| 472 |
+
"eval_steps_per_second": 2.621,
|
| 473 |
+
"step": 3100
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.12,
|
| 477 |
+
"learning_rate": 6.250732278851787e-05,
|
| 478 |
+
"loss": 0.1663,
|
| 479 |
+
"step": 3200
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.12,
|
| 483 |
+
"eval_accuracy": 0.9380511938051194,
|
| 484 |
+
"eval_loss": 0.2038552463054657,
|
| 485 |
+
"eval_runtime": 57.0481,
|
| 486 |
+
"eval_samples_per_second": 81.493,
|
| 487 |
+
"eval_steps_per_second": 2.559,
|
| 488 |
+
"step": 3200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.16,
|
| 492 |
+
"learning_rate": 6.133567662565906e-05,
|
| 493 |
+
"loss": 0.1847,
|
| 494 |
+
"step": 3300
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.16,
|
| 498 |
+
"eval_accuracy": 0.9266508926650893,
|
| 499 |
+
"eval_loss": 0.2347552329301834,
|
| 500 |
+
"eval_runtime": 56.4891,
|
| 501 |
+
"eval_samples_per_second": 82.299,
|
| 502 |
+
"eval_steps_per_second": 2.585,
|
| 503 |
+
"step": 3300
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.2,
|
| 507 |
+
"learning_rate": 6.016403046280023e-05,
|
| 508 |
+
"loss": 0.1809,
|
| 509 |
+
"step": 3400
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.2,
|
| 513 |
+
"eval_accuracy": 0.9236394923639493,
|
| 514 |
+
"eval_loss": 0.24315237998962402,
|
| 515 |
+
"eval_runtime": 54.6687,
|
| 516 |
+
"eval_samples_per_second": 85.04,
|
| 517 |
+
"eval_steps_per_second": 2.671,
|
| 518 |
+
"step": 3400
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.23,
|
| 522 |
+
"learning_rate": 5.899238429994142e-05,
|
| 523 |
+
"loss": 0.1787,
|
| 524 |
+
"step": 3500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.23,
|
| 528 |
+
"eval_accuracy": 0.9339642933964294,
|
| 529 |
+
"eval_loss": 0.21847452223300934,
|
| 530 |
+
"eval_runtime": 54.0398,
|
| 531 |
+
"eval_samples_per_second": 86.029,
|
| 532 |
+
"eval_steps_per_second": 2.702,
|
| 533 |
+
"step": 3500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.27,
|
| 537 |
+
"learning_rate": 5.782073813708261e-05,
|
| 538 |
+
"loss": 0.183,
|
| 539 |
+
"step": 3600
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.27,
|
| 543 |
+
"eval_accuracy": 0.9363303936330394,
|
| 544 |
+
"eval_loss": 0.20778249204158783,
|
| 545 |
+
"eval_runtime": 54.441,
|
| 546 |
+
"eval_samples_per_second": 85.395,
|
| 547 |
+
"eval_steps_per_second": 2.682,
|
| 548 |
+
"step": 3600
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.3,
|
| 552 |
+
"learning_rate": 5.664909197422379e-05,
|
| 553 |
+
"loss": 0.1704,
|
| 554 |
+
"step": 3700
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.3,
|
| 558 |
+
"eval_accuracy": 0.9152505915250592,
|
| 559 |
+
"eval_loss": 0.23343944549560547,
|
| 560 |
+
"eval_runtime": 56.1215,
|
| 561 |
+
"eval_samples_per_second": 82.838,
|
| 562 |
+
"eval_steps_per_second": 2.601,
|
| 563 |
+
"step": 3700
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.34,
|
| 567 |
+
"learning_rate": 5.547744581136497e-05,
|
| 568 |
+
"loss": 0.2002,
|
| 569 |
+
"step": 3800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.34,
|
| 573 |
+
"eval_accuracy": 0.9212733921273392,
|
| 574 |
+
"eval_loss": 0.23881135880947113,
|
| 575 |
+
"eval_runtime": 54.8777,
|
| 576 |
+
"eval_samples_per_second": 84.716,
|
| 577 |
+
"eval_steps_per_second": 2.66,
|
| 578 |
+
"step": 3800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.37,
|
| 582 |
+
"learning_rate": 5.430579964850615e-05,
|
| 583 |
+
"loss": 0.1787,
|
| 584 |
+
"step": 3900
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.37,
|
| 588 |
+
"eval_accuracy": 0.9260055926005593,
|
| 589 |
+
"eval_loss": 0.22407278418540955,
|
| 590 |
+
"eval_runtime": 54.5169,
|
| 591 |
+
"eval_samples_per_second": 85.276,
|
| 592 |
+
"eval_steps_per_second": 2.678,
|
| 593 |
+
"step": 3900
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.41,
|
| 597 |
+
"learning_rate": 5.3134153485647345e-05,
|
| 598 |
+
"loss": 0.1757,
|
| 599 |
+
"step": 4000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.41,
|
| 603 |
+
"eval_accuracy": 0.9324585932458593,
|
| 604 |
+
"eval_loss": 0.2097584456205368,
|
| 605 |
+
"eval_runtime": 54.3298,
|
| 606 |
+
"eval_samples_per_second": 85.57,
|
| 607 |
+
"eval_steps_per_second": 2.687,
|
| 608 |
+
"step": 4000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.44,
|
| 612 |
+
"learning_rate": 5.1962507322788524e-05,
|
| 613 |
+
"loss": 0.1667,
|
| 614 |
+
"step": 4100
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.44,
|
| 618 |
+
"eval_accuracy": 0.9348246934824693,
|
| 619 |
+
"eval_loss": 0.21198517084121704,
|
| 620 |
+
"eval_runtime": 53.7704,
|
| 621 |
+
"eval_samples_per_second": 86.46,
|
| 622 |
+
"eval_steps_per_second": 2.715,
|
| 623 |
+
"step": 4100
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.48,
|
| 627 |
+
"learning_rate": 5.07908611599297e-05,
|
| 628 |
+
"loss": 0.2078,
|
| 629 |
+
"step": 4200
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.48,
|
| 633 |
+
"eval_accuracy": 0.9348246934824693,
|
| 634 |
+
"eval_loss": 0.2187454104423523,
|
| 635 |
+
"eval_runtime": 54.7943,
|
| 636 |
+
"eval_samples_per_second": 84.845,
|
| 637 |
+
"eval_steps_per_second": 2.665,
|
| 638 |
+
"step": 4200
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.51,
|
| 642 |
+
"learning_rate": 4.961921499707089e-05,
|
| 643 |
+
"loss": 0.1775,
|
| 644 |
+
"step": 4300
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.51,
|
| 648 |
+
"eval_accuracy": 0.9294471929447193,
|
| 649 |
+
"eval_loss": 0.226194366812706,
|
| 650 |
+
"eval_runtime": 54.2742,
|
| 651 |
+
"eval_samples_per_second": 85.658,
|
| 652 |
+
"eval_steps_per_second": 2.69,
|
| 653 |
+
"step": 4300
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.55,
|
| 657 |
+
"learning_rate": 4.844756883421207e-05,
|
| 658 |
+
"loss": 0.1771,
|
| 659 |
+
"step": 4400
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.55,
|
| 663 |
+
"eval_accuracy": 0.9311679931167993,
|
| 664 |
+
"eval_loss": 0.2125757783651352,
|
| 665 |
+
"eval_runtime": 53.3871,
|
| 666 |
+
"eval_samples_per_second": 87.081,
|
| 667 |
+
"eval_steps_per_second": 2.735,
|
| 668 |
+
"step": 4400
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.58,
|
| 672 |
+
"learning_rate": 4.727592267135325e-05,
|
| 673 |
+
"loss": 0.158,
|
| 674 |
+
"step": 4500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.58,
|
| 678 |
+
"eval_accuracy": 0.9343944934394494,
|
| 679 |
+
"eval_loss": 0.20714816451072693,
|
| 680 |
+
"eval_runtime": 53.7213,
|
| 681 |
+
"eval_samples_per_second": 86.539,
|
| 682 |
+
"eval_steps_per_second": 2.718,
|
| 683 |
+
"step": 4500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.62,
|
| 687 |
+
"learning_rate": 4.610427650849444e-05,
|
| 688 |
+
"loss": 0.1792,
|
| 689 |
+
"step": 4600
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.62,
|
| 693 |
+
"eval_accuracy": 0.9275112927511293,
|
| 694 |
+
"eval_loss": 0.227621927857399,
|
| 695 |
+
"eval_runtime": 54.9746,
|
| 696 |
+
"eval_samples_per_second": 84.566,
|
| 697 |
+
"eval_steps_per_second": 2.656,
|
| 698 |
+
"step": 4600
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.65,
|
| 702 |
+
"learning_rate": 4.4932630345635615e-05,
|
| 703 |
+
"loss": 0.1523,
|
| 704 |
+
"step": 4700
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.65,
|
| 708 |
+
"eval_accuracy": 0.9268659926865993,
|
| 709 |
+
"eval_loss": 0.21835899353027344,
|
| 710 |
+
"eval_runtime": 55.0826,
|
| 711 |
+
"eval_samples_per_second": 84.4,
|
| 712 |
+
"eval_steps_per_second": 2.651,
|
| 713 |
+
"step": 4700
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.69,
|
| 717 |
+
"learning_rate": 4.37609841827768e-05,
|
| 718 |
+
"loss": 0.1739,
|
| 719 |
+
"step": 4800
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.69,
|
| 723 |
+
"eval_accuracy": 0.9322434932243493,
|
| 724 |
+
"eval_loss": 0.22359773516654968,
|
| 725 |
+
"eval_runtime": 53.2692,
|
| 726 |
+
"eval_samples_per_second": 87.274,
|
| 727 |
+
"eval_steps_per_second": 2.741,
|
| 728 |
+
"step": 4800
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 1.72,
|
| 732 |
+
"learning_rate": 4.2589338019917986e-05,
|
| 733 |
+
"loss": 0.1638,
|
| 734 |
+
"step": 4900
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.72,
|
| 738 |
+
"eval_accuracy": 0.9402021940202194,
|
| 739 |
+
"eval_loss": 0.18819227814674377,
|
| 740 |
+
"eval_runtime": 52.562,
|
| 741 |
+
"eval_samples_per_second": 88.448,
|
| 742 |
+
"eval_steps_per_second": 2.778,
|
| 743 |
+
"step": 4900
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 1.76,
|
| 747 |
+
"learning_rate": 4.141769185705917e-05,
|
| 748 |
+
"loss": 0.1653,
|
| 749 |
+
"step": 5000
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 1.76,
|
| 753 |
+
"eval_accuracy": 0.9309528930952893,
|
| 754 |
+
"eval_loss": 0.21739357709884644,
|
| 755 |
+
"eval_runtime": 54.6403,
|
| 756 |
+
"eval_samples_per_second": 85.084,
|
| 757 |
+
"eval_steps_per_second": 2.672,
|
| 758 |
+
"step": 5000
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 1.79,
|
| 762 |
+
"learning_rate": 4.024604569420035e-05,
|
| 763 |
+
"loss": 0.1584,
|
| 764 |
+
"step": 5100
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 1.79,
|
| 768 |
+
"eval_accuracy": 0.9384813938481393,
|
| 769 |
+
"eval_loss": 0.197902649641037,
|
| 770 |
+
"eval_runtime": 54.1444,
|
| 771 |
+
"eval_samples_per_second": 85.863,
|
| 772 |
+
"eval_steps_per_second": 2.696,
|
| 773 |
+
"step": 5100
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.83,
|
| 777 |
+
"learning_rate": 3.9074399531341535e-05,
|
| 778 |
+
"loss": 0.1621,
|
| 779 |
+
"step": 5200
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 1.83,
|
| 783 |
+
"eval_accuracy": 0.9371907937190793,
|
| 784 |
+
"eval_loss": 0.20193301141262054,
|
| 785 |
+
"eval_runtime": 52.6121,
|
| 786 |
+
"eval_samples_per_second": 88.364,
|
| 787 |
+
"eval_steps_per_second": 2.775,
|
| 788 |
+
"step": 5200
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 1.86,
|
| 792 |
+
"learning_rate": 3.790275336848272e-05,
|
| 793 |
+
"loss": 0.156,
|
| 794 |
+
"step": 5300
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.86,
|
| 798 |
+
"eval_accuracy": 0.9322434932243493,
|
| 799 |
+
"eval_loss": 0.20995856821537018,
|
| 800 |
+
"eval_runtime": 52.8452,
|
| 801 |
+
"eval_samples_per_second": 87.974,
|
| 802 |
+
"eval_steps_per_second": 2.763,
|
| 803 |
+
"step": 5300
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 1.9,
|
| 807 |
+
"learning_rate": 3.6731107205623906e-05,
|
| 808 |
+
"loss": 0.1819,
|
| 809 |
+
"step": 5400
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 1.9,
|
| 813 |
+
"eval_accuracy": 0.9384813938481393,
|
| 814 |
+
"eval_loss": 0.18913036584854126,
|
| 815 |
+
"eval_runtime": 53.1008,
|
| 816 |
+
"eval_samples_per_second": 87.55,
|
| 817 |
+
"eval_steps_per_second": 2.749,
|
| 818 |
+
"step": 5400
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 1.93,
|
| 822 |
+
"learning_rate": 3.5559461042765085e-05,
|
| 823 |
+
"loss": 0.1676,
|
| 824 |
+
"step": 5500
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 1.93,
|
| 828 |
+
"eval_accuracy": 0.9397719939771993,
|
| 829 |
+
"eval_loss": 0.18966327607631683,
|
| 830 |
+
"eval_runtime": 54.5409,
|
| 831 |
+
"eval_samples_per_second": 85.239,
|
| 832 |
+
"eval_steps_per_second": 2.677,
|
| 833 |
+
"step": 5500
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 1.97,
|
| 837 |
+
"learning_rate": 3.438781487990627e-05,
|
| 838 |
+
"loss": 0.1675,
|
| 839 |
+
"step": 5600
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 1.97,
|
| 843 |
+
"eval_accuracy": 0.9393417939341794,
|
| 844 |
+
"eval_loss": 0.1928705871105194,
|
| 845 |
+
"eval_runtime": 54.2748,
|
| 846 |
+
"eval_samples_per_second": 85.657,
|
| 847 |
+
"eval_steps_per_second": 2.69,
|
| 848 |
+
"step": 5600
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.0,
|
| 852 |
+
"learning_rate": 3.3216168717047456e-05,
|
| 853 |
+
"loss": 0.1389,
|
| 854 |
+
"step": 5700
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.0,
|
| 858 |
+
"eval_accuracy": 0.9389115938911594,
|
| 859 |
+
"eval_loss": 0.1925574094057083,
|
| 860 |
+
"eval_runtime": 53.5821,
|
| 861 |
+
"eval_samples_per_second": 86.764,
|
| 862 |
+
"eval_steps_per_second": 2.725,
|
| 863 |
+
"step": 5700
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 2.04,
|
| 867 |
+
"learning_rate": 3.204452255418864e-05,
|
| 868 |
+
"loss": 0.1217,
|
| 869 |
+
"step": 5800
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 2.04,
|
| 873 |
+
"eval_accuracy": 0.9324585932458593,
|
| 874 |
+
"eval_loss": 0.1982860118150711,
|
| 875 |
+
"eval_runtime": 53.4582,
|
| 876 |
+
"eval_samples_per_second": 86.965,
|
| 877 |
+
"eval_steps_per_second": 2.731,
|
| 878 |
+
"step": 5800
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.07,
|
| 882 |
+
"learning_rate": 3.087287639132982e-05,
|
| 883 |
+
"loss": 0.1158,
|
| 884 |
+
"step": 5900
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.07,
|
| 888 |
+
"eval_accuracy": 0.9391266939126693,
|
| 889 |
+
"eval_loss": 0.1853022575378418,
|
| 890 |
+
"eval_runtime": 52.3558,
|
| 891 |
+
"eval_samples_per_second": 88.796,
|
| 892 |
+
"eval_steps_per_second": 2.789,
|
| 893 |
+
"step": 5900
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.11,
|
| 897 |
+
"learning_rate": 2.9701230228471005e-05,
|
| 898 |
+
"loss": 0.1375,
|
| 899 |
+
"step": 6000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.11,
|
| 903 |
+
"eval_accuracy": 0.9371907937190793,
|
| 904 |
+
"eval_loss": 0.19718600809574127,
|
| 905 |
+
"eval_runtime": 53.8918,
|
| 906 |
+
"eval_samples_per_second": 86.265,
|
| 907 |
+
"eval_steps_per_second": 2.709,
|
| 908 |
+
"step": 6000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 2.14,
|
| 912 |
+
"learning_rate": 2.8541300527240778e-05,
|
| 913 |
+
"loss": 0.1195,
|
| 914 |
+
"step": 6100
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.14,
|
| 918 |
+
"eval_accuracy": 0.9384813938481393,
|
| 919 |
+
"eval_loss": 0.19445277750492096,
|
| 920 |
+
"eval_runtime": 53.8229,
|
| 921 |
+
"eval_samples_per_second": 86.376,
|
| 922 |
+
"eval_steps_per_second": 2.713,
|
| 923 |
+
"step": 6100
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 2.18,
|
| 927 |
+
"learning_rate": 2.7369654364381957e-05,
|
| 928 |
+
"loss": 0.1249,
|
| 929 |
+
"step": 6200
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 2.18,
|
| 933 |
+
"eval_accuracy": 0.9350397935039794,
|
| 934 |
+
"eval_loss": 0.19001764059066772,
|
| 935 |
+
"eval_runtime": 52.3182,
|
| 936 |
+
"eval_samples_per_second": 88.86,
|
| 937 |
+
"eval_steps_per_second": 2.791,
|
| 938 |
+
"step": 6200
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.21,
|
| 942 |
+
"learning_rate": 2.619800820152314e-05,
|
| 943 |
+
"loss": 0.1204,
|
| 944 |
+
"step": 6300
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 2.21,
|
| 948 |
+
"eval_accuracy": 0.9324585932458593,
|
| 949 |
+
"eval_loss": 0.20320840179920197,
|
| 950 |
+
"eval_runtime": 52.8746,
|
| 951 |
+
"eval_samples_per_second": 87.925,
|
| 952 |
+
"eval_steps_per_second": 2.761,
|
| 953 |
+
"step": 6300
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 2.25,
|
| 957 |
+
"learning_rate": 2.5026362038664324e-05,
|
| 958 |
+
"loss": 0.122,
|
| 959 |
+
"step": 6400
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 2.25,
|
| 963 |
+
"eval_accuracy": 0.9376209937620994,
|
| 964 |
+
"eval_loss": 0.17533761262893677,
|
| 965 |
+
"eval_runtime": 52.222,
|
| 966 |
+
"eval_samples_per_second": 89.024,
|
| 967 |
+
"eval_steps_per_second": 2.796,
|
| 968 |
+
"step": 6400
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 2.28,
|
| 972 |
+
"learning_rate": 2.385471587580551e-05,
|
| 973 |
+
"loss": 0.1136,
|
| 974 |
+
"step": 6500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.28,
|
| 978 |
+
"eval_accuracy": 0.9406323940632394,
|
| 979 |
+
"eval_loss": 0.18234318494796753,
|
| 980 |
+
"eval_runtime": 53.2472,
|
| 981 |
+
"eval_samples_per_second": 87.31,
|
| 982 |
+
"eval_steps_per_second": 2.742,
|
| 983 |
+
"step": 6500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.32,
|
| 987 |
+
"learning_rate": 2.268306971294669e-05,
|
| 988 |
+
"loss": 0.125,
|
| 989 |
+
"step": 6600
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 2.32,
|
| 993 |
+
"eval_accuracy": 0.9391266939126693,
|
| 994 |
+
"eval_loss": 0.1814049780368805,
|
| 995 |
+
"eval_runtime": 55.3063,
|
| 996 |
+
"eval_samples_per_second": 84.059,
|
| 997 |
+
"eval_steps_per_second": 2.64,
|
| 998 |
+
"step": 6600
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 2.36,
|
| 1002 |
+
"learning_rate": 2.1511423550087877e-05,
|
| 1003 |
+
"loss": 0.1142,
|
| 1004 |
+
"step": 6700
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.36,
|
| 1008 |
+
"eval_accuracy": 0.9402021940202194,
|
| 1009 |
+
"eval_loss": 0.1924043744802475,
|
| 1010 |
+
"eval_runtime": 53.3253,
|
| 1011 |
+
"eval_samples_per_second": 87.182,
|
| 1012 |
+
"eval_steps_per_second": 2.738,
|
| 1013 |
+
"step": 6700
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.39,
|
| 1017 |
+
"learning_rate": 2.033977738722906e-05,
|
| 1018 |
+
"loss": 0.1258,
|
| 1019 |
+
"step": 6800
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 2.39,
|
| 1023 |
+
"eval_accuracy": 0.9421380942138095,
|
| 1024 |
+
"eval_loss": 0.1804322451353073,
|
| 1025 |
+
"eval_runtime": 52.0681,
|
| 1026 |
+
"eval_samples_per_second": 89.287,
|
| 1027 |
+
"eval_steps_per_second": 2.804,
|
| 1028 |
+
"step": 6800
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 2.43,
|
| 1032 |
+
"learning_rate": 1.916813122437024e-05,
|
| 1033 |
+
"loss": 0.1178,
|
| 1034 |
+
"step": 6900
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.43,
|
| 1038 |
+
"eval_accuracy": 0.9374058937405894,
|
| 1039 |
+
"eval_loss": 0.18380628526210785,
|
| 1040 |
+
"eval_runtime": 52.0076,
|
| 1041 |
+
"eval_samples_per_second": 89.391,
|
| 1042 |
+
"eval_steps_per_second": 2.807,
|
| 1043 |
+
"step": 6900
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 2.46,
|
| 1047 |
+
"learning_rate": 1.7996485061511426e-05,
|
| 1048 |
+
"loss": 0.1093,
|
| 1049 |
+
"step": 7000
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.46,
|
| 1053 |
+
"eval_accuracy": 0.9391266939126693,
|
| 1054 |
+
"eval_loss": 0.17910005152225494,
|
| 1055 |
+
"eval_runtime": 51.873,
|
| 1056 |
+
"eval_samples_per_second": 89.623,
|
| 1057 |
+
"eval_steps_per_second": 2.815,
|
| 1058 |
+
"step": 7000
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 2.5,
|
| 1062 |
+
"learning_rate": 1.6824838898652608e-05,
|
| 1063 |
+
"loss": 0.1069,
|
| 1064 |
+
"step": 7100
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 2.5,
|
| 1068 |
+
"eval_accuracy": 0.9391266939126693,
|
| 1069 |
+
"eval_loss": 0.18617549538612366,
|
| 1070 |
+
"eval_runtime": 54.5914,
|
| 1071 |
+
"eval_samples_per_second": 85.16,
|
| 1072 |
+
"eval_steps_per_second": 2.674,
|
| 1073 |
+
"step": 7100
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 2.53,
|
| 1077 |
+
"learning_rate": 1.565319273579379e-05,
|
| 1078 |
+
"loss": 0.1361,
|
| 1079 |
+
"step": 7200
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 2.53,
|
| 1083 |
+
"eval_accuracy": 0.9417078941707894,
|
| 1084 |
+
"eval_loss": 0.17183491587638855,
|
| 1085 |
+
"eval_runtime": 53.9807,
|
| 1086 |
+
"eval_samples_per_second": 86.123,
|
| 1087 |
+
"eval_steps_per_second": 2.705,
|
| 1088 |
+
"step": 7200
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.57,
|
| 1092 |
+
"learning_rate": 1.4481546572934974e-05,
|
| 1093 |
+
"loss": 0.1167,
|
| 1094 |
+
"step": 7300
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 2.57,
|
| 1098 |
+
"eval_accuracy": 0.9380511938051194,
|
| 1099 |
+
"eval_loss": 0.18089379370212555,
|
| 1100 |
+
"eval_runtime": 52.2028,
|
| 1101 |
+
"eval_samples_per_second": 89.056,
|
| 1102 |
+
"eval_steps_per_second": 2.797,
|
| 1103 |
+
"step": 7300
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.6,
|
| 1107 |
+
"learning_rate": 1.3309900410076156e-05,
|
| 1108 |
+
"loss": 0.127,
|
| 1109 |
+
"step": 7400
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.6,
|
| 1113 |
+
"eval_accuracy": 0.9445041944504194,
|
| 1114 |
+
"eval_loss": 0.17267315089702606,
|
| 1115 |
+
"eval_runtime": 51.7533,
|
| 1116 |
+
"eval_samples_per_second": 89.83,
|
| 1117 |
+
"eval_steps_per_second": 2.821,
|
| 1118 |
+
"step": 7400
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 2.64,
|
| 1122 |
+
"learning_rate": 1.2138254247217341e-05,
|
| 1123 |
+
"loss": 0.1215,
|
| 1124 |
+
"step": 7500
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.64,
|
| 1128 |
+
"eval_accuracy": 0.9402021940202194,
|
| 1129 |
+
"eval_loss": 0.18060338497161865,
|
| 1130 |
+
"eval_runtime": 53.2058,
|
| 1131 |
+
"eval_samples_per_second": 87.378,
|
| 1132 |
+
"eval_steps_per_second": 2.744,
|
| 1133 |
+
"step": 7500
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 2.67,
|
| 1137 |
+
"learning_rate": 1.0966608084358525e-05,
|
| 1138 |
+
"loss": 0.1162,
|
| 1139 |
+
"step": 7600
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 2.67,
|
| 1143 |
+
"eval_accuracy": 0.9404172940417294,
|
| 1144 |
+
"eval_loss": 0.18343867361545563,
|
| 1145 |
+
"eval_runtime": 56.0804,
|
| 1146 |
+
"eval_samples_per_second": 82.899,
|
| 1147 |
+
"eval_steps_per_second": 2.603,
|
| 1148 |
+
"step": 7600
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 2.71,
|
| 1152 |
+
"learning_rate": 9.794961921499708e-06,
|
| 1153 |
+
"loss": 0.1182,
|
| 1154 |
+
"step": 7700
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.71,
|
| 1158 |
+
"eval_accuracy": 0.9406323940632394,
|
| 1159 |
+
"eval_loss": 0.17546848952770233,
|
| 1160 |
+
"eval_runtime": 53.4141,
|
| 1161 |
+
"eval_samples_per_second": 87.037,
|
| 1162 |
+
"eval_steps_per_second": 2.733,
|
| 1163 |
+
"step": 7700
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 2.74,
|
| 1167 |
+
"learning_rate": 8.62331575864089e-06,
|
| 1168 |
+
"loss": 0.1179,
|
| 1169 |
+
"step": 7800
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 2.74,
|
| 1173 |
+
"eval_accuracy": 0.9410625941062594,
|
| 1174 |
+
"eval_loss": 0.179013192653656,
|
| 1175 |
+
"eval_runtime": 54.9709,
|
| 1176 |
+
"eval_samples_per_second": 84.572,
|
| 1177 |
+
"eval_steps_per_second": 2.656,
|
| 1178 |
+
"step": 7800
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 2.78,
|
| 1182 |
+
"learning_rate": 7.451669595782074e-06,
|
| 1183 |
+
"loss": 0.1012,
|
| 1184 |
+
"step": 7900
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 2.78,
|
| 1188 |
+
"eval_accuracy": 0.9427833942783395,
|
| 1189 |
+
"eval_loss": 0.17139938473701477,
|
| 1190 |
+
"eval_runtime": 53.4602,
|
| 1191 |
+
"eval_samples_per_second": 86.962,
|
| 1192 |
+
"eval_steps_per_second": 2.731,
|
| 1193 |
+
"step": 7900
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.81,
|
| 1197 |
+
"learning_rate": 6.280023432923257e-06,
|
| 1198 |
+
"loss": 0.1186,
|
| 1199 |
+
"step": 8000
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 2.81,
|
| 1203 |
+
"eval_accuracy": 0.9393417939341794,
|
| 1204 |
+
"eval_loss": 0.17887155711650848,
|
| 1205 |
+
"eval_runtime": 53.0073,
|
| 1206 |
+
"eval_samples_per_second": 87.705,
|
| 1207 |
+
"eval_steps_per_second": 2.754,
|
| 1208 |
+
"step": 8000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.85,
|
| 1212 |
+
"learning_rate": 5.1083772700644406e-06,
|
| 1213 |
+
"loss": 0.1305,
|
| 1214 |
+
"step": 8100
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.85,
|
| 1218 |
+
"eval_accuracy": 0.9408474940847494,
|
| 1219 |
+
"eval_loss": 0.17335866391658783,
|
| 1220 |
+
"eval_runtime": 52.8785,
|
| 1221 |
+
"eval_samples_per_second": 87.919,
|
| 1222 |
+
"eval_steps_per_second": 2.761,
|
| 1223 |
+
"step": 8100
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 2.88,
|
| 1227 |
+
"learning_rate": 3.936731107205624e-06,
|
| 1228 |
+
"loss": 0.1126,
|
| 1229 |
+
"step": 8200
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.88,
|
| 1233 |
+
"eval_accuracy": 0.9397719939771993,
|
| 1234 |
+
"eval_loss": 0.1753973364830017,
|
| 1235 |
+
"eval_runtime": 51.7413,
|
| 1236 |
+
"eval_samples_per_second": 89.851,
|
| 1237 |
+
"eval_steps_per_second": 2.822,
|
| 1238 |
+
"step": 8200
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 2.92,
|
| 1242 |
+
"learning_rate": 2.776801405975396e-06,
|
| 1243 |
+
"loss": 0.1128,
|
| 1244 |
+
"step": 8300
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 2.92,
|
| 1248 |
+
"eval_accuracy": 0.9445041944504194,
|
| 1249 |
+
"eval_loss": 0.1688772737979889,
|
| 1250 |
+
"eval_runtime": 51.7644,
|
| 1251 |
+
"eval_samples_per_second": 89.811,
|
| 1252 |
+
"eval_steps_per_second": 2.82,
|
| 1253 |
+
"step": 8300
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 2.95,
|
| 1257 |
+
"learning_rate": 1.605155243116579e-06,
|
| 1258 |
+
"loss": 0.1108,
|
| 1259 |
+
"step": 8400
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 2.95,
|
| 1263 |
+
"eval_accuracy": 0.9442890944289094,
|
| 1264 |
+
"eval_loss": 0.16805602610111237,
|
| 1265 |
+
"eval_runtime": 53.4934,
|
| 1266 |
+
"eval_samples_per_second": 86.908,
|
| 1267 |
+
"eval_steps_per_second": 2.729,
|
| 1268 |
+
"step": 8400
|
| 1269 |
+
}
|
| 1270 |
+
],
|
| 1271 |
+
"max_steps": 8535,
|
| 1272 |
+
"num_train_epochs": 3,
|
| 1273 |
+
"total_flos": 2.083300191455087e+19,
|
| 1274 |
+
"trial_name": null,
|
| 1275 |
+
"trial_params": null
|
| 1276 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5168ed0d536ebe9e05710e2a42e701d765e5d4a39b79bec7337527ad79f3b6f4
|
| 3 |
+
size 3963
|