Upload folder using huggingface_hub
#1
by
PranomVignesh
- 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 +1105 -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 sha256:988da3d053e5377b39bb3d8ff5a44e37cb92cf461a3f9c8d6926266973875b87
|
| 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:f245fdf60dcda05f6d43b8d978c2a3444607fd13a6776a617a62f6919ab1afc7
|
| 3 |
+
size 343379437
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:040e1fc422c0a8be218aff6765f3632a90cc5bfe30d3447acf55f588b1fbf767
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9459d5dc5e462d70441715c28d43c4681f3df8583f6a53745a7dc38d7f20ad4
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.2977927625179291,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-1280",
|
| 4 |
+
"epoch": 3.963963963963964,
|
| 5 |
+
"global_step": 1320,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 0.0001984984984984985,
|
| 13 |
+
"loss": 3.6277,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 0.00019699699699699701,
|
| 19 |
+
"loss": 3.5588,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 0.0001954954954954955,
|
| 25 |
+
"loss": 3.4115,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 0.00019399399399399402,
|
| 31 |
+
"loss": 3.2498,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"eval_accuracy": 0.22024983563445102,
|
| 37 |
+
"eval_loss": 3.1079554557800293,
|
| 38 |
+
"eval_runtime": 25.4224,
|
| 39 |
+
"eval_samples_per_second": 59.829,
|
| 40 |
+
"eval_steps_per_second": 7.513,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.15,
|
| 45 |
+
"learning_rate": 0.0001924924924924925,
|
| 46 |
+
"loss": 2.967,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.18,
|
| 51 |
+
"learning_rate": 0.000190990990990991,
|
| 52 |
+
"loss": 2.8969,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.21,
|
| 57 |
+
"learning_rate": 0.0001894894894894895,
|
| 58 |
+
"loss": 2.7153,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.24,
|
| 63 |
+
"learning_rate": 0.000187987987987988,
|
| 64 |
+
"loss": 2.5076,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.24,
|
| 69 |
+
"eval_accuracy": 0.4339250493096647,
|
| 70 |
+
"eval_loss": 2.4336094856262207,
|
| 71 |
+
"eval_runtime": 25.9183,
|
| 72 |
+
"eval_samples_per_second": 58.684,
|
| 73 |
+
"eval_steps_per_second": 7.369,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.27,
|
| 78 |
+
"learning_rate": 0.0001864864864864865,
|
| 79 |
+
"loss": 2.3504,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.3,
|
| 84 |
+
"learning_rate": 0.000184984984984985,
|
| 85 |
+
"loss": 2.2198,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.33,
|
| 90 |
+
"learning_rate": 0.0001834834834834835,
|
| 91 |
+
"loss": 2.1227,
|
| 92 |
+
"step": 110
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.36,
|
| 96 |
+
"learning_rate": 0.000181981981981982,
|
| 97 |
+
"loss": 1.9345,
|
| 98 |
+
"step": 120
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.36,
|
| 102 |
+
"eval_accuracy": 0.6226166995397765,
|
| 103 |
+
"eval_loss": 1.8898930549621582,
|
| 104 |
+
"eval_runtime": 25.7004,
|
| 105 |
+
"eval_samples_per_second": 59.182,
|
| 106 |
+
"eval_steps_per_second": 7.432,
|
| 107 |
+
"step": 120
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.39,
|
| 111 |
+
"learning_rate": 0.0001804804804804805,
|
| 112 |
+
"loss": 1.8725,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.42,
|
| 117 |
+
"learning_rate": 0.00017897897897897898,
|
| 118 |
+
"loss": 1.6834,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.45,
|
| 123 |
+
"learning_rate": 0.0001774774774774775,
|
| 124 |
+
"loss": 1.6183,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.48,
|
| 129 |
+
"learning_rate": 0.000175975975975976,
|
| 130 |
+
"loss": 1.4224,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.48,
|
| 135 |
+
"eval_accuracy": 0.673241288625904,
|
| 136 |
+
"eval_loss": 1.5380345582962036,
|
| 137 |
+
"eval_runtime": 26.3631,
|
| 138 |
+
"eval_samples_per_second": 57.694,
|
| 139 |
+
"eval_steps_per_second": 7.245,
|
| 140 |
+
"step": 160
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.51,
|
| 144 |
+
"learning_rate": 0.0001744744744744745,
|
| 145 |
+
"loss": 1.5553,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.54,
|
| 150 |
+
"learning_rate": 0.000172972972972973,
|
| 151 |
+
"loss": 1.3173,
|
| 152 |
+
"step": 180
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.57,
|
| 156 |
+
"learning_rate": 0.00017147147147147148,
|
| 157 |
+
"loss": 1.2917,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.6,
|
| 162 |
+
"learning_rate": 0.00016996996996997,
|
| 163 |
+
"loss": 1.2626,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6,
|
| 168 |
+
"eval_accuracy": 0.7370151216305062,
|
| 169 |
+
"eval_loss": 1.2467007637023926,
|
| 170 |
+
"eval_runtime": 25.735,
|
| 171 |
+
"eval_samples_per_second": 59.102,
|
| 172 |
+
"eval_steps_per_second": 7.422,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.63,
|
| 177 |
+
"learning_rate": 0.00016846846846846846,
|
| 178 |
+
"loss": 1.0941,
|
| 179 |
+
"step": 210
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.66,
|
| 183 |
+
"learning_rate": 0.00016696696696696697,
|
| 184 |
+
"loss": 1.1499,
|
| 185 |
+
"step": 220
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.69,
|
| 189 |
+
"learning_rate": 0.00016546546546546546,
|
| 190 |
+
"loss": 1.085,
|
| 191 |
+
"step": 230
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.72,
|
| 195 |
+
"learning_rate": 0.00016396396396396395,
|
| 196 |
+
"loss": 1.0447,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.72,
|
| 201 |
+
"eval_accuracy": 0.7633136094674556,
|
| 202 |
+
"eval_loss": 1.0867702960968018,
|
| 203 |
+
"eval_runtime": 25.9624,
|
| 204 |
+
"eval_samples_per_second": 58.585,
|
| 205 |
+
"eval_steps_per_second": 7.357,
|
| 206 |
+
"step": 240
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.75,
|
| 210 |
+
"learning_rate": 0.00016246246246246247,
|
| 211 |
+
"loss": 0.9169,
|
| 212 |
+
"step": 250
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.78,
|
| 216 |
+
"learning_rate": 0.00016096096096096096,
|
| 217 |
+
"loss": 1.0707,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.81,
|
| 222 |
+
"learning_rate": 0.00015945945945945947,
|
| 223 |
+
"loss": 0.8938,
|
| 224 |
+
"step": 270
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.84,
|
| 228 |
+
"learning_rate": 0.00015795795795795796,
|
| 229 |
+
"loss": 0.9403,
|
| 230 |
+
"step": 280
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.84,
|
| 234 |
+
"eval_accuracy": 0.8007889546351085,
|
| 235 |
+
"eval_loss": 0.8639808297157288,
|
| 236 |
+
"eval_runtime": 25.817,
|
| 237 |
+
"eval_samples_per_second": 58.915,
|
| 238 |
+
"eval_steps_per_second": 7.398,
|
| 239 |
+
"step": 280
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.87,
|
| 243 |
+
"learning_rate": 0.00015645645645645645,
|
| 244 |
+
"loss": 0.8592,
|
| 245 |
+
"step": 290
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.9,
|
| 249 |
+
"learning_rate": 0.00015495495495495496,
|
| 250 |
+
"loss": 0.9383,
|
| 251 |
+
"step": 300
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.93,
|
| 255 |
+
"learning_rate": 0.00015345345345345345,
|
| 256 |
+
"loss": 0.8804,
|
| 257 |
+
"step": 310
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.96,
|
| 261 |
+
"learning_rate": 0.00015195195195195194,
|
| 262 |
+
"loss": 0.7259,
|
| 263 |
+
"step": 320
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.96,
|
| 267 |
+
"eval_accuracy": 0.8198553583168968,
|
| 268 |
+
"eval_loss": 0.7540761828422546,
|
| 269 |
+
"eval_runtime": 25.7,
|
| 270 |
+
"eval_samples_per_second": 59.183,
|
| 271 |
+
"eval_steps_per_second": 7.432,
|
| 272 |
+
"step": 320
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.99,
|
| 276 |
+
"learning_rate": 0.00015045045045045046,
|
| 277 |
+
"loss": 0.7308,
|
| 278 |
+
"step": 330
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.02,
|
| 282 |
+
"learning_rate": 0.00014894894894894895,
|
| 283 |
+
"loss": 0.6628,
|
| 284 |
+
"step": 340
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.05,
|
| 288 |
+
"learning_rate": 0.00014744744744744746,
|
| 289 |
+
"loss": 0.6611,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.08,
|
| 294 |
+
"learning_rate": 0.00014594594594594595,
|
| 295 |
+
"loss": 0.7276,
|
| 296 |
+
"step": 360
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.08,
|
| 300 |
+
"eval_accuracy": 0.8500986193293886,
|
| 301 |
+
"eval_loss": 0.6682031154632568,
|
| 302 |
+
"eval_runtime": 26.3636,
|
| 303 |
+
"eval_samples_per_second": 57.693,
|
| 304 |
+
"eval_steps_per_second": 7.245,
|
| 305 |
+
"step": 360
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.11,
|
| 309 |
+
"learning_rate": 0.00014444444444444444,
|
| 310 |
+
"loss": 0.6113,
|
| 311 |
+
"step": 370
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.14,
|
| 315 |
+
"learning_rate": 0.00014294294294294295,
|
| 316 |
+
"loss": 0.545,
|
| 317 |
+
"step": 380
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.17,
|
| 321 |
+
"learning_rate": 0.00014144144144144144,
|
| 322 |
+
"loss": 0.682,
|
| 323 |
+
"step": 390
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.2,
|
| 327 |
+
"learning_rate": 0.00013993993993993996,
|
| 328 |
+
"loss": 0.5643,
|
| 329 |
+
"step": 400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.2,
|
| 333 |
+
"eval_accuracy": 0.8303747534516766,
|
| 334 |
+
"eval_loss": 0.6452277302742004,
|
| 335 |
+
"eval_runtime": 25.857,
|
| 336 |
+
"eval_samples_per_second": 58.824,
|
| 337 |
+
"eval_steps_per_second": 7.387,
|
| 338 |
+
"step": 400
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.23,
|
| 342 |
+
"learning_rate": 0.00013843843843843845,
|
| 343 |
+
"loss": 0.5002,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.26,
|
| 348 |
+
"learning_rate": 0.00013693693693693693,
|
| 349 |
+
"loss": 0.5067,
|
| 350 |
+
"step": 420
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.29,
|
| 354 |
+
"learning_rate": 0.00013543543543543545,
|
| 355 |
+
"loss": 0.5445,
|
| 356 |
+
"step": 430
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.32,
|
| 360 |
+
"learning_rate": 0.00013393393393393394,
|
| 361 |
+
"loss": 0.6703,
|
| 362 |
+
"step": 440
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.32,
|
| 366 |
+
"eval_accuracy": 0.7988165680473372,
|
| 367 |
+
"eval_loss": 0.6957046985626221,
|
| 368 |
+
"eval_runtime": 25.2844,
|
| 369 |
+
"eval_samples_per_second": 60.156,
|
| 370 |
+
"eval_steps_per_second": 7.554,
|
| 371 |
+
"step": 440
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.35,
|
| 375 |
+
"learning_rate": 0.00013243243243243243,
|
| 376 |
+
"loss": 0.8127,
|
| 377 |
+
"step": 450
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.38,
|
| 381 |
+
"learning_rate": 0.00013093093093093094,
|
| 382 |
+
"loss": 0.567,
|
| 383 |
+
"step": 460
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.41,
|
| 387 |
+
"learning_rate": 0.00012942942942942943,
|
| 388 |
+
"loss": 0.5575,
|
| 389 |
+
"step": 470
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.44,
|
| 393 |
+
"learning_rate": 0.00012792792792792795,
|
| 394 |
+
"loss": 0.396,
|
| 395 |
+
"step": 480
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.44,
|
| 399 |
+
"eval_accuracy": 0.8428665351742275,
|
| 400 |
+
"eval_loss": 0.5446497797966003,
|
| 401 |
+
"eval_runtime": 25.6496,
|
| 402 |
+
"eval_samples_per_second": 59.299,
|
| 403 |
+
"eval_steps_per_second": 7.447,
|
| 404 |
+
"step": 480
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.47,
|
| 408 |
+
"learning_rate": 0.00012642642642642644,
|
| 409 |
+
"loss": 0.4975,
|
| 410 |
+
"step": 490
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.5,
|
| 414 |
+
"learning_rate": 0.00012492492492492492,
|
| 415 |
+
"loss": 0.3971,
|
| 416 |
+
"step": 500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.53,
|
| 420 |
+
"learning_rate": 0.00012342342342342344,
|
| 421 |
+
"loss": 0.469,
|
| 422 |
+
"step": 510
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.56,
|
| 426 |
+
"learning_rate": 0.00012192192192192193,
|
| 427 |
+
"loss": 0.4277,
|
| 428 |
+
"step": 520
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.56,
|
| 432 |
+
"eval_accuracy": 0.8408941485864563,
|
| 433 |
+
"eval_loss": 0.5659409165382385,
|
| 434 |
+
"eval_runtime": 25.2836,
|
| 435 |
+
"eval_samples_per_second": 60.157,
|
| 436 |
+
"eval_steps_per_second": 7.554,
|
| 437 |
+
"step": 520
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.59,
|
| 441 |
+
"learning_rate": 0.00012042042042042043,
|
| 442 |
+
"loss": 0.4984,
|
| 443 |
+
"step": 530
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.62,
|
| 447 |
+
"learning_rate": 0.00011891891891891893,
|
| 448 |
+
"loss": 0.476,
|
| 449 |
+
"step": 540
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.65,
|
| 453 |
+
"learning_rate": 0.00011741741741741743,
|
| 454 |
+
"loss": 0.5402,
|
| 455 |
+
"step": 550
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.68,
|
| 459 |
+
"learning_rate": 0.00011591591591591592,
|
| 460 |
+
"loss": 0.457,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.68,
|
| 465 |
+
"eval_accuracy": 0.8527284681130834,
|
| 466 |
+
"eval_loss": 0.5437894463539124,
|
| 467 |
+
"eval_runtime": 25.9766,
|
| 468 |
+
"eval_samples_per_second": 58.553,
|
| 469 |
+
"eval_steps_per_second": 7.353,
|
| 470 |
+
"step": 560
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.71,
|
| 474 |
+
"learning_rate": 0.00011441441441441443,
|
| 475 |
+
"loss": 0.3039,
|
| 476 |
+
"step": 570
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.74,
|
| 480 |
+
"learning_rate": 0.00011291291291291293,
|
| 481 |
+
"loss": 0.4621,
|
| 482 |
+
"step": 580
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.77,
|
| 486 |
+
"learning_rate": 0.00011141141141141143,
|
| 487 |
+
"loss": 0.4584,
|
| 488 |
+
"step": 590
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.8,
|
| 492 |
+
"learning_rate": 0.00010990990990990993,
|
| 493 |
+
"loss": 0.5632,
|
| 494 |
+
"step": 600
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.8,
|
| 498 |
+
"eval_accuracy": 0.8547008547008547,
|
| 499 |
+
"eval_loss": 0.49320539832115173,
|
| 500 |
+
"eval_runtime": 25.6823,
|
| 501 |
+
"eval_samples_per_second": 59.224,
|
| 502 |
+
"eval_steps_per_second": 7.437,
|
| 503 |
+
"step": 600
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.83,
|
| 507 |
+
"learning_rate": 0.00010840840840840842,
|
| 508 |
+
"loss": 0.4798,
|
| 509 |
+
"step": 610
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.86,
|
| 513 |
+
"learning_rate": 0.00010690690690690692,
|
| 514 |
+
"loss": 0.3991,
|
| 515 |
+
"step": 620
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.89,
|
| 519 |
+
"learning_rate": 0.0001054054054054054,
|
| 520 |
+
"loss": 0.4815,
|
| 521 |
+
"step": 630
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.92,
|
| 525 |
+
"learning_rate": 0.0001039039039039039,
|
| 526 |
+
"loss": 0.4066,
|
| 527 |
+
"step": 640
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.92,
|
| 531 |
+
"eval_accuracy": 0.8658777120315582,
|
| 532 |
+
"eval_loss": 0.4579479694366455,
|
| 533 |
+
"eval_runtime": 25.9931,
|
| 534 |
+
"eval_samples_per_second": 58.516,
|
| 535 |
+
"eval_steps_per_second": 7.348,
|
| 536 |
+
"step": 640
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.95,
|
| 540 |
+
"learning_rate": 0.0001024024024024024,
|
| 541 |
+
"loss": 0.5159,
|
| 542 |
+
"step": 650
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.98,
|
| 546 |
+
"learning_rate": 0.00010090090090090089,
|
| 547 |
+
"loss": 0.4886,
|
| 548 |
+
"step": 660
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.01,
|
| 552 |
+
"learning_rate": 9.93993993993994e-05,
|
| 553 |
+
"loss": 0.2916,
|
| 554 |
+
"step": 670
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.04,
|
| 558 |
+
"learning_rate": 9.789789789789791e-05,
|
| 559 |
+
"loss": 0.2505,
|
| 560 |
+
"step": 680
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.04,
|
| 564 |
+
"eval_accuracy": 0.8665351742274819,
|
| 565 |
+
"eval_loss": 0.4546054005622864,
|
| 566 |
+
"eval_runtime": 26.0755,
|
| 567 |
+
"eval_samples_per_second": 58.331,
|
| 568 |
+
"eval_steps_per_second": 7.325,
|
| 569 |
+
"step": 680
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 2.07,
|
| 573 |
+
"learning_rate": 9.639639639639641e-05,
|
| 574 |
+
"loss": 0.3156,
|
| 575 |
+
"step": 690
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 2.1,
|
| 579 |
+
"learning_rate": 9.48948948948949e-05,
|
| 580 |
+
"loss": 0.375,
|
| 581 |
+
"step": 700
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 2.13,
|
| 585 |
+
"learning_rate": 9.33933933933934e-05,
|
| 586 |
+
"loss": 0.2663,
|
| 587 |
+
"step": 710
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 2.16,
|
| 591 |
+
"learning_rate": 9.18918918918919e-05,
|
| 592 |
+
"loss": 0.3181,
|
| 593 |
+
"step": 720
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.16,
|
| 597 |
+
"eval_accuracy": 0.8586456278763971,
|
| 598 |
+
"eval_loss": 0.4709266424179077,
|
| 599 |
+
"eval_runtime": 26.2379,
|
| 600 |
+
"eval_samples_per_second": 57.97,
|
| 601 |
+
"eval_steps_per_second": 7.28,
|
| 602 |
+
"step": 720
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.19,
|
| 606 |
+
"learning_rate": 9.039039039039039e-05,
|
| 607 |
+
"loss": 0.2628,
|
| 608 |
+
"step": 730
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.22,
|
| 612 |
+
"learning_rate": 8.888888888888889e-05,
|
| 613 |
+
"loss": 0.1784,
|
| 614 |
+
"step": 740
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.25,
|
| 618 |
+
"learning_rate": 8.738738738738738e-05,
|
| 619 |
+
"loss": 0.357,
|
| 620 |
+
"step": 750
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.28,
|
| 624 |
+
"learning_rate": 8.588588588588588e-05,
|
| 625 |
+
"loss": 0.1931,
|
| 626 |
+
"step": 760
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.28,
|
| 630 |
+
"eval_accuracy": 0.8593030900723209,
|
| 631 |
+
"eval_loss": 0.45762282609939575,
|
| 632 |
+
"eval_runtime": 25.7501,
|
| 633 |
+
"eval_samples_per_second": 59.068,
|
| 634 |
+
"eval_steps_per_second": 7.417,
|
| 635 |
+
"step": 760
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.31,
|
| 639 |
+
"learning_rate": 8.438438438438439e-05,
|
| 640 |
+
"loss": 0.2865,
|
| 641 |
+
"step": 770
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.34,
|
| 645 |
+
"learning_rate": 8.288288288288289e-05,
|
| 646 |
+
"loss": 0.3125,
|
| 647 |
+
"step": 780
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 2.37,
|
| 651 |
+
"learning_rate": 8.138138138138138e-05,
|
| 652 |
+
"loss": 0.417,
|
| 653 |
+
"step": 790
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 2.4,
|
| 657 |
+
"learning_rate": 7.987987987987988e-05,
|
| 658 |
+
"loss": 0.288,
|
| 659 |
+
"step": 800
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 2.4,
|
| 663 |
+
"eval_accuracy": 0.8763971071663379,
|
| 664 |
+
"eval_loss": 0.41621989011764526,
|
| 665 |
+
"eval_runtime": 25.9323,
|
| 666 |
+
"eval_samples_per_second": 58.653,
|
| 667 |
+
"eval_steps_per_second": 7.365,
|
| 668 |
+
"step": 800
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.43,
|
| 672 |
+
"learning_rate": 7.837837837837838e-05,
|
| 673 |
+
"loss": 0.3603,
|
| 674 |
+
"step": 810
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 2.46,
|
| 678 |
+
"learning_rate": 7.687687687687688e-05,
|
| 679 |
+
"loss": 0.2386,
|
| 680 |
+
"step": 820
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.49,
|
| 684 |
+
"learning_rate": 7.537537537537538e-05,
|
| 685 |
+
"loss": 0.2035,
|
| 686 |
+
"step": 830
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.52,
|
| 690 |
+
"learning_rate": 7.387387387387387e-05,
|
| 691 |
+
"loss": 0.2315,
|
| 692 |
+
"step": 840
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.52,
|
| 696 |
+
"eval_accuracy": 0.8895463510848126,
|
| 697 |
+
"eval_loss": 0.3602614402770996,
|
| 698 |
+
"eval_runtime": 26.3037,
|
| 699 |
+
"eval_samples_per_second": 57.825,
|
| 700 |
+
"eval_steps_per_second": 7.261,
|
| 701 |
+
"step": 840
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 2.55,
|
| 705 |
+
"learning_rate": 7.237237237237238e-05,
|
| 706 |
+
"loss": 0.239,
|
| 707 |
+
"step": 850
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 2.58,
|
| 711 |
+
"learning_rate": 7.087087087087088e-05,
|
| 712 |
+
"loss": 0.2514,
|
| 713 |
+
"step": 860
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 2.61,
|
| 717 |
+
"learning_rate": 6.936936936936938e-05,
|
| 718 |
+
"loss": 0.3601,
|
| 719 |
+
"step": 870
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 2.64,
|
| 723 |
+
"learning_rate": 6.786786786786787e-05,
|
| 724 |
+
"loss": 0.1812,
|
| 725 |
+
"step": 880
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.64,
|
| 729 |
+
"eval_accuracy": 0.8823142669296515,
|
| 730 |
+
"eval_loss": 0.40812087059020996,
|
| 731 |
+
"eval_runtime": 25.5461,
|
| 732 |
+
"eval_samples_per_second": 59.539,
|
| 733 |
+
"eval_steps_per_second": 7.477,
|
| 734 |
+
"step": 880
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.67,
|
| 738 |
+
"learning_rate": 6.636636636636637e-05,
|
| 739 |
+
"loss": 0.2621,
|
| 740 |
+
"step": 890
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.7,
|
| 744 |
+
"learning_rate": 6.486486486486487e-05,
|
| 745 |
+
"loss": 0.2284,
|
| 746 |
+
"step": 900
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.73,
|
| 750 |
+
"learning_rate": 6.336336336336337e-05,
|
| 751 |
+
"loss": 0.1624,
|
| 752 |
+
"step": 910
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.76,
|
| 756 |
+
"learning_rate": 6.186186186186186e-05,
|
| 757 |
+
"loss": 0.2661,
|
| 758 |
+
"step": 920
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.76,
|
| 762 |
+
"eval_accuracy": 0.8777120315581854,
|
| 763 |
+
"eval_loss": 0.3957211375236511,
|
| 764 |
+
"eval_runtime": 26.3972,
|
| 765 |
+
"eval_samples_per_second": 57.62,
|
| 766 |
+
"eval_steps_per_second": 7.236,
|
| 767 |
+
"step": 920
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.79,
|
| 771 |
+
"learning_rate": 6.0360360360360365e-05,
|
| 772 |
+
"loss": 0.2434,
|
| 773 |
+
"step": 930
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 2.82,
|
| 777 |
+
"learning_rate": 5.8858858858858854e-05,
|
| 778 |
+
"loss": 0.2894,
|
| 779 |
+
"step": 940
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 2.85,
|
| 783 |
+
"learning_rate": 5.7357357357357356e-05,
|
| 784 |
+
"loss": 0.1421,
|
| 785 |
+
"step": 950
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 2.88,
|
| 789 |
+
"learning_rate": 5.585585585585585e-05,
|
| 790 |
+
"loss": 0.2632,
|
| 791 |
+
"step": 960
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.88,
|
| 795 |
+
"eval_accuracy": 0.8915187376725838,
|
| 796 |
+
"eval_loss": 0.34952232241630554,
|
| 797 |
+
"eval_runtime": 25.2354,
|
| 798 |
+
"eval_samples_per_second": 60.272,
|
| 799 |
+
"eval_steps_per_second": 7.569,
|
| 800 |
+
"step": 960
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.91,
|
| 804 |
+
"learning_rate": 5.435435435435435e-05,
|
| 805 |
+
"loss": 0.2474,
|
| 806 |
+
"step": 970
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.94,
|
| 810 |
+
"learning_rate": 5.2852852852852855e-05,
|
| 811 |
+
"loss": 0.2458,
|
| 812 |
+
"step": 980
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.97,
|
| 816 |
+
"learning_rate": 5.135135135135135e-05,
|
| 817 |
+
"loss": 0.2121,
|
| 818 |
+
"step": 990
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.0,
|
| 822 |
+
"learning_rate": 4.984984984984985e-05,
|
| 823 |
+
"loss": 0.215,
|
| 824 |
+
"step": 1000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.0,
|
| 828 |
+
"eval_accuracy": 0.8915187376725838,
|
| 829 |
+
"eval_loss": 0.3721879720687866,
|
| 830 |
+
"eval_runtime": 26.0936,
|
| 831 |
+
"eval_samples_per_second": 58.29,
|
| 832 |
+
"eval_steps_per_second": 7.32,
|
| 833 |
+
"step": 1000
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 3.03,
|
| 837 |
+
"learning_rate": 4.834834834834835e-05,
|
| 838 |
+
"loss": 0.1788,
|
| 839 |
+
"step": 1010
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 3.06,
|
| 843 |
+
"learning_rate": 4.684684684684685e-05,
|
| 844 |
+
"loss": 0.1671,
|
| 845 |
+
"step": 1020
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 3.09,
|
| 849 |
+
"learning_rate": 4.5345345345345345e-05,
|
| 850 |
+
"loss": 0.1663,
|
| 851 |
+
"step": 1030
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 3.12,
|
| 855 |
+
"learning_rate": 4.384384384384385e-05,
|
| 856 |
+
"loss": 0.1661,
|
| 857 |
+
"step": 1040
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 3.12,
|
| 861 |
+
"eval_accuracy": 0.8888888888888888,
|
| 862 |
+
"eval_loss": 0.3638674318790436,
|
| 863 |
+
"eval_runtime": 25.7736,
|
| 864 |
+
"eval_samples_per_second": 59.014,
|
| 865 |
+
"eval_steps_per_second": 7.411,
|
| 866 |
+
"step": 1040
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.15,
|
| 870 |
+
"learning_rate": 4.234234234234234e-05,
|
| 871 |
+
"loss": 0.1734,
|
| 872 |
+
"step": 1050
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.18,
|
| 876 |
+
"learning_rate": 4.0840840840840845e-05,
|
| 877 |
+
"loss": 0.1525,
|
| 878 |
+
"step": 1060
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.21,
|
| 882 |
+
"learning_rate": 3.933933933933934e-05,
|
| 883 |
+
"loss": 0.1397,
|
| 884 |
+
"step": 1070
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.24,
|
| 888 |
+
"learning_rate": 3.783783783783784e-05,
|
| 889 |
+
"loss": 0.1164,
|
| 890 |
+
"step": 1080
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.24,
|
| 894 |
+
"eval_accuracy": 0.9013806706114399,
|
| 895 |
+
"eval_loss": 0.32475772500038147,
|
| 896 |
+
"eval_runtime": 25.7546,
|
| 897 |
+
"eval_samples_per_second": 59.057,
|
| 898 |
+
"eval_steps_per_second": 7.416,
|
| 899 |
+
"step": 1080
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 3.27,
|
| 903 |
+
"learning_rate": 3.633633633633634e-05,
|
| 904 |
+
"loss": 0.176,
|
| 905 |
+
"step": 1090
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 3.3,
|
| 909 |
+
"learning_rate": 3.483483483483483e-05,
|
| 910 |
+
"loss": 0.1248,
|
| 911 |
+
"step": 1100
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 3.33,
|
| 915 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 916 |
+
"loss": 0.1025,
|
| 917 |
+
"step": 1110
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 3.36,
|
| 921 |
+
"learning_rate": 3.183183183183183e-05,
|
| 922 |
+
"loss": 0.1745,
|
| 923 |
+
"step": 1120
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.36,
|
| 927 |
+
"eval_accuracy": 0.8948060486522025,
|
| 928 |
+
"eval_loss": 0.33917945623397827,
|
| 929 |
+
"eval_runtime": 26.0362,
|
| 930 |
+
"eval_samples_per_second": 58.419,
|
| 931 |
+
"eval_steps_per_second": 7.336,
|
| 932 |
+
"step": 1120
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.39,
|
| 936 |
+
"learning_rate": 3.0330330330330332e-05,
|
| 937 |
+
"loss": 0.2151,
|
| 938 |
+
"step": 1130
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.42,
|
| 942 |
+
"learning_rate": 2.882882882882883e-05,
|
| 943 |
+
"loss": 0.1135,
|
| 944 |
+
"step": 1140
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.45,
|
| 948 |
+
"learning_rate": 2.732732732732733e-05,
|
| 949 |
+
"loss": 0.1307,
|
| 950 |
+
"step": 1150
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 3.48,
|
| 954 |
+
"learning_rate": 2.582582582582583e-05,
|
| 955 |
+
"loss": 0.1347,
|
| 956 |
+
"step": 1160
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 3.48,
|
| 960 |
+
"eval_accuracy": 0.8980933596318211,
|
| 961 |
+
"eval_loss": 0.33266809582710266,
|
| 962 |
+
"eval_runtime": 25.5437,
|
| 963 |
+
"eval_samples_per_second": 59.545,
|
| 964 |
+
"eval_steps_per_second": 7.477,
|
| 965 |
+
"step": 1160
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.51,
|
| 969 |
+
"learning_rate": 2.4324324324324327e-05,
|
| 970 |
+
"loss": 0.1395,
|
| 971 |
+
"step": 1170
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.54,
|
| 975 |
+
"learning_rate": 2.2822822822822822e-05,
|
| 976 |
+
"loss": 0.1506,
|
| 977 |
+
"step": 1180
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 3.57,
|
| 981 |
+
"learning_rate": 2.132132132132132e-05,
|
| 982 |
+
"loss": 0.1833,
|
| 983 |
+
"step": 1190
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 3.6,
|
| 987 |
+
"learning_rate": 1.981981981981982e-05,
|
| 988 |
+
"loss": 0.1362,
|
| 989 |
+
"step": 1200
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 3.6,
|
| 993 |
+
"eval_accuracy": 0.9105851413543721,
|
| 994 |
+
"eval_loss": 0.3018592596054077,
|
| 995 |
+
"eval_runtime": 26.0978,
|
| 996 |
+
"eval_samples_per_second": 58.281,
|
| 997 |
+
"eval_steps_per_second": 7.319,
|
| 998 |
+
"step": 1200
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.63,
|
| 1002 |
+
"learning_rate": 1.831831831831832e-05,
|
| 1003 |
+
"loss": 0.1402,
|
| 1004 |
+
"step": 1210
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 3.66,
|
| 1008 |
+
"learning_rate": 1.6816816816816817e-05,
|
| 1009 |
+
"loss": 0.142,
|
| 1010 |
+
"step": 1220
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 3.69,
|
| 1014 |
+
"learning_rate": 1.5315315315315316e-05,
|
| 1015 |
+
"loss": 0.1422,
|
| 1016 |
+
"step": 1230
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.72,
|
| 1020 |
+
"learning_rate": 1.3813813813813815e-05,
|
| 1021 |
+
"loss": 0.127,
|
| 1022 |
+
"step": 1240
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.72,
|
| 1026 |
+
"eval_accuracy": 0.9072978303747534,
|
| 1027 |
+
"eval_loss": 0.3087291419506073,
|
| 1028 |
+
"eval_runtime": 25.0476,
|
| 1029 |
+
"eval_samples_per_second": 60.724,
|
| 1030 |
+
"eval_steps_per_second": 7.625,
|
| 1031 |
+
"step": 1240
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 3.75,
|
| 1035 |
+
"learning_rate": 1.2312312312312313e-05,
|
| 1036 |
+
"loss": 0.1435,
|
| 1037 |
+
"step": 1250
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 3.78,
|
| 1041 |
+
"learning_rate": 1.0810810810810812e-05,
|
| 1042 |
+
"loss": 0.1236,
|
| 1043 |
+
"step": 1260
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 3.81,
|
| 1047 |
+
"learning_rate": 9.309309309309309e-06,
|
| 1048 |
+
"loss": 0.1167,
|
| 1049 |
+
"step": 1270
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.84,
|
| 1053 |
+
"learning_rate": 7.807807807807808e-06,
|
| 1054 |
+
"loss": 0.1041,
|
| 1055 |
+
"step": 1280
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 3.84,
|
| 1059 |
+
"eval_accuracy": 0.9099276791584484,
|
| 1060 |
+
"eval_loss": 0.2977927625179291,
|
| 1061 |
+
"eval_runtime": 26.1338,
|
| 1062 |
+
"eval_samples_per_second": 58.2,
|
| 1063 |
+
"eval_steps_per_second": 7.309,
|
| 1064 |
+
"step": 1280
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.87,
|
| 1068 |
+
"learning_rate": 6.306306306306306e-06,
|
| 1069 |
+
"loss": 0.1486,
|
| 1070 |
+
"step": 1290
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.9,
|
| 1074 |
+
"learning_rate": 4.804804804804805e-06,
|
| 1075 |
+
"loss": 0.1316,
|
| 1076 |
+
"step": 1300
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.93,
|
| 1080 |
+
"learning_rate": 3.3033033033033035e-06,
|
| 1081 |
+
"loss": 0.1035,
|
| 1082 |
+
"step": 1310
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 3.96,
|
| 1086 |
+
"learning_rate": 1.801801801801802e-06,
|
| 1087 |
+
"loss": 0.106,
|
| 1088 |
+
"step": 1320
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.96,
|
| 1092 |
+
"eval_accuracy": 0.9112426035502958,
|
| 1093 |
+
"eval_loss": 0.2991219162940979,
|
| 1094 |
+
"eval_runtime": 25.2949,
|
| 1095 |
+
"eval_samples_per_second": 60.131,
|
| 1096 |
+
"eval_steps_per_second": 7.551,
|
| 1097 |
+
"step": 1320
|
| 1098 |
+
}
|
| 1099 |
+
],
|
| 1100 |
+
"max_steps": 1332,
|
| 1101 |
+
"num_train_epochs": 4,
|
| 1102 |
+
"total_flos": 1.6343682786726543e+18,
|
| 1103 |
+
"trial_name": null,
|
| 1104 |
+
"trial_params": null
|
| 1105 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c889fe7ac0f743a0537f10a56930a278af37a45454b9b3c7caf790fe6c39851
|
| 3 |
+
size 3963
|