Commit
•
1ad31c5
1
Parent(s):
156ae5a
trained oxford-flowers
Browse files- README.md +78 -0
- all_results.json +8 -0
- config.json +232 -0
- model.safetensors +3 -0
- preprocessor_config.json +22 -0
- runs/Jan01_02-35-15_a5b36194356f/events.out.tfevents.1704076520.a5b36194356f.3303.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +1255 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
+
tags:
|
| 5 |
+
- image-classification
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: vit-base-flowers102
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# vit-base-flowers102
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the nelorth/oxford-flowers dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0770
|
| 22 |
+
- Accuracy: 0.9853
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0002
|
| 42 |
+
- train_batch_size: 16
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- num_epochs: 4
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| 2.5779 | 0.22 | 100 | 2.8895 | 0.7775 |
|
| 55 |
+
| 1.2226 | 0.45 | 200 | 1.5942 | 0.9255 |
|
| 56 |
+
| 0.606 | 0.67 | 300 | 0.8012 | 0.9529 |
|
| 57 |
+
| 0.3413 | 0.89 | 400 | 0.4845 | 0.9706 |
|
| 58 |
+
| 0.1571 | 1.11 | 500 | 0.2611 | 0.9814 |
|
| 59 |
+
| 0.1237 | 1.34 | 600 | 0.1691 | 0.9784 |
|
| 60 |
+
| 0.049 | 1.56 | 700 | 0.1146 | 0.9892 |
|
| 61 |
+
| 0.0763 | 1.78 | 800 | 0.1209 | 0.9863 |
|
| 62 |
+
| 0.0864 | 2.0 | 900 | 0.1223 | 0.9804 |
|
| 63 |
+
| 0.0786 | 2.23 | 1000 | 0.1075 | 0.9833 |
|
| 64 |
+
| 0.0269 | 2.45 | 1100 | 0.0919 | 0.9843 |
|
| 65 |
+
| 0.0178 | 2.67 | 1200 | 0.0795 | 0.9873 |
|
| 66 |
+
| 0.0165 | 2.9 | 1300 | 0.0727 | 0.9873 |
|
| 67 |
+
| 0.0144 | 3.12 | 1400 | 0.0784 | 0.9853 |
|
| 68 |
+
| 0.0138 | 3.34 | 1500 | 0.0759 | 0.9853 |
|
| 69 |
+
| 0.0135 | 3.56 | 1600 | 0.0737 | 0.9863 |
|
| 70 |
+
| 0.0123 | 3.79 | 1700 | 0.0770 | 0.9853 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.35.2
|
| 76 |
+
- Pytorch 2.1.0+cu121
|
| 77 |
+
- Datasets 2.16.1
|
| 78 |
+
- Tokenizers 0.15.0
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 2.2241519461722194e+18,
|
| 4 |
+
"train_loss": 0.4137112680814314,
|
| 5 |
+
"train_runtime": 1023.9197,
|
| 6 |
+
"train_samples_per_second": 28.006,
|
| 7 |
+
"train_steps_per_second": 1.754
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "1",
|
| 13 |
+
"1": "10",
|
| 14 |
+
"10": "16",
|
| 15 |
+
"100": "98",
|
| 16 |
+
"101": "99",
|
| 17 |
+
"11": "17",
|
| 18 |
+
"12": "18",
|
| 19 |
+
"13": "19",
|
| 20 |
+
"14": "2",
|
| 21 |
+
"15": "20",
|
| 22 |
+
"16": "21",
|
| 23 |
+
"17": "22",
|
| 24 |
+
"18": "23",
|
| 25 |
+
"19": "24",
|
| 26 |
+
"2": "100",
|
| 27 |
+
"20": "25",
|
| 28 |
+
"21": "26",
|
| 29 |
+
"22": "27",
|
| 30 |
+
"23": "28",
|
| 31 |
+
"24": "29",
|
| 32 |
+
"25": "3",
|
| 33 |
+
"26": "30",
|
| 34 |
+
"27": "31",
|
| 35 |
+
"28": "32",
|
| 36 |
+
"29": "33",
|
| 37 |
+
"3": "101",
|
| 38 |
+
"30": "34",
|
| 39 |
+
"31": "35",
|
| 40 |
+
"32": "36",
|
| 41 |
+
"33": "37",
|
| 42 |
+
"34": "38",
|
| 43 |
+
"35": "39",
|
| 44 |
+
"36": "4",
|
| 45 |
+
"37": "40",
|
| 46 |
+
"38": "41",
|
| 47 |
+
"39": "42",
|
| 48 |
+
"4": "102",
|
| 49 |
+
"40": "43",
|
| 50 |
+
"41": "44",
|
| 51 |
+
"42": "45",
|
| 52 |
+
"43": "46",
|
| 53 |
+
"44": "47",
|
| 54 |
+
"45": "48",
|
| 55 |
+
"46": "49",
|
| 56 |
+
"47": "5",
|
| 57 |
+
"48": "50",
|
| 58 |
+
"49": "51",
|
| 59 |
+
"5": "11",
|
| 60 |
+
"50": "52",
|
| 61 |
+
"51": "53",
|
| 62 |
+
"52": "54",
|
| 63 |
+
"53": "55",
|
| 64 |
+
"54": "56",
|
| 65 |
+
"55": "57",
|
| 66 |
+
"56": "58",
|
| 67 |
+
"57": "59",
|
| 68 |
+
"58": "6",
|
| 69 |
+
"59": "60",
|
| 70 |
+
"6": "12",
|
| 71 |
+
"60": "61",
|
| 72 |
+
"61": "62",
|
| 73 |
+
"62": "63",
|
| 74 |
+
"63": "64",
|
| 75 |
+
"64": "65",
|
| 76 |
+
"65": "66",
|
| 77 |
+
"66": "67",
|
| 78 |
+
"67": "68",
|
| 79 |
+
"68": "69",
|
| 80 |
+
"69": "7",
|
| 81 |
+
"7": "13",
|
| 82 |
+
"70": "70",
|
| 83 |
+
"71": "71",
|
| 84 |
+
"72": "72",
|
| 85 |
+
"73": "73",
|
| 86 |
+
"74": "74",
|
| 87 |
+
"75": "75",
|
| 88 |
+
"76": "76",
|
| 89 |
+
"77": "77",
|
| 90 |
+
"78": "78",
|
| 91 |
+
"79": "79",
|
| 92 |
+
"8": "14",
|
| 93 |
+
"80": "8",
|
| 94 |
+
"81": "80",
|
| 95 |
+
"82": "81",
|
| 96 |
+
"83": "82",
|
| 97 |
+
"84": "83",
|
| 98 |
+
"85": "84",
|
| 99 |
+
"86": "85",
|
| 100 |
+
"87": "86",
|
| 101 |
+
"88": "87",
|
| 102 |
+
"89": "88",
|
| 103 |
+
"9": "15",
|
| 104 |
+
"90": "89",
|
| 105 |
+
"91": "9",
|
| 106 |
+
"92": "90",
|
| 107 |
+
"93": "91",
|
| 108 |
+
"94": "92",
|
| 109 |
+
"95": "93",
|
| 110 |
+
"96": "94",
|
| 111 |
+
"97": "95",
|
| 112 |
+
"98": "96",
|
| 113 |
+
"99": "97"
|
| 114 |
+
},
|
| 115 |
+
"image_size": 224,
|
| 116 |
+
"initializer_range": 0.02,
|
| 117 |
+
"intermediate_size": 3072,
|
| 118 |
+
"label2id": {
|
| 119 |
+
"1": "0",
|
| 120 |
+
"10": "1",
|
| 121 |
+
"100": "2",
|
| 122 |
+
"101": "3",
|
| 123 |
+
"102": "4",
|
| 124 |
+
"11": "5",
|
| 125 |
+
"12": "6",
|
| 126 |
+
"13": "7",
|
| 127 |
+
"14": "8",
|
| 128 |
+
"15": "9",
|
| 129 |
+
"16": "10",
|
| 130 |
+
"17": "11",
|
| 131 |
+
"18": "12",
|
| 132 |
+
"19": "13",
|
| 133 |
+
"2": "14",
|
| 134 |
+
"20": "15",
|
| 135 |
+
"21": "16",
|
| 136 |
+
"22": "17",
|
| 137 |
+
"23": "18",
|
| 138 |
+
"24": "19",
|
| 139 |
+
"25": "20",
|
| 140 |
+
"26": "21",
|
| 141 |
+
"27": "22",
|
| 142 |
+
"28": "23",
|
| 143 |
+
"29": "24",
|
| 144 |
+
"3": "25",
|
| 145 |
+
"30": "26",
|
| 146 |
+
"31": "27",
|
| 147 |
+
"32": "28",
|
| 148 |
+
"33": "29",
|
| 149 |
+
"34": "30",
|
| 150 |
+
"35": "31",
|
| 151 |
+
"36": "32",
|
| 152 |
+
"37": "33",
|
| 153 |
+
"38": "34",
|
| 154 |
+
"39": "35",
|
| 155 |
+
"4": "36",
|
| 156 |
+
"40": "37",
|
| 157 |
+
"41": "38",
|
| 158 |
+
"42": "39",
|
| 159 |
+
"43": "40",
|
| 160 |
+
"44": "41",
|
| 161 |
+
"45": "42",
|
| 162 |
+
"46": "43",
|
| 163 |
+
"47": "44",
|
| 164 |
+
"48": "45",
|
| 165 |
+
"49": "46",
|
| 166 |
+
"5": "47",
|
| 167 |
+
"50": "48",
|
| 168 |
+
"51": "49",
|
| 169 |
+
"52": "50",
|
| 170 |
+
"53": "51",
|
| 171 |
+
"54": "52",
|
| 172 |
+
"55": "53",
|
| 173 |
+
"56": "54",
|
| 174 |
+
"57": "55",
|
| 175 |
+
"58": "56",
|
| 176 |
+
"59": "57",
|
| 177 |
+
"6": "58",
|
| 178 |
+
"60": "59",
|
| 179 |
+
"61": "60",
|
| 180 |
+
"62": "61",
|
| 181 |
+
"63": "62",
|
| 182 |
+
"64": "63",
|
| 183 |
+
"65": "64",
|
| 184 |
+
"66": "65",
|
| 185 |
+
"67": "66",
|
| 186 |
+
"68": "67",
|
| 187 |
+
"69": "68",
|
| 188 |
+
"7": "69",
|
| 189 |
+
"70": "70",
|
| 190 |
+
"71": "71",
|
| 191 |
+
"72": "72",
|
| 192 |
+
"73": "73",
|
| 193 |
+
"74": "74",
|
| 194 |
+
"75": "75",
|
| 195 |
+
"76": "76",
|
| 196 |
+
"77": "77",
|
| 197 |
+
"78": "78",
|
| 198 |
+
"79": "79",
|
| 199 |
+
"8": "80",
|
| 200 |
+
"80": "81",
|
| 201 |
+
"81": "82",
|
| 202 |
+
"82": "83",
|
| 203 |
+
"83": "84",
|
| 204 |
+
"84": "85",
|
| 205 |
+
"85": "86",
|
| 206 |
+
"86": "87",
|
| 207 |
+
"87": "88",
|
| 208 |
+
"88": "89",
|
| 209 |
+
"89": "90",
|
| 210 |
+
"9": "91",
|
| 211 |
+
"90": "92",
|
| 212 |
+
"91": "93",
|
| 213 |
+
"92": "94",
|
| 214 |
+
"93": "95",
|
| 215 |
+
"94": "96",
|
| 216 |
+
"95": "97",
|
| 217 |
+
"96": "98",
|
| 218 |
+
"97": "99",
|
| 219 |
+
"98": "100",
|
| 220 |
+
"99": "101"
|
| 221 |
+
},
|
| 222 |
+
"layer_norm_eps": 1e-12,
|
| 223 |
+
"model_type": "vit",
|
| 224 |
+
"num_attention_heads": 12,
|
| 225 |
+
"num_channels": 3,
|
| 226 |
+
"num_hidden_layers": 12,
|
| 227 |
+
"patch_size": 16,
|
| 228 |
+
"problem_type": "single_label_classification",
|
| 229 |
+
"qkv_bias": true,
|
| 230 |
+
"torch_dtype": "float32",
|
| 231 |
+
"transformers_version": "4.35.2"
|
| 232 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76bee5ebdb3ee0625a0175f243125c94ee5cbf2b7f2dc1052a23c96c38f9d363
|
| 3 |
+
size 343531584
|
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 |
+
}
|
runs/Jan01_02-35-15_a5b36194356f/events.out.tfevents.1704076520.a5b36194356f.3303.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ef94daf7dd39eb906248e7c9e8e5e53d11e49d68ee860fa7151c375f48f1659
|
| 3 |
+
size 41282
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 4.0,
|
| 3 |
+
"total_flos": 2.2241519461722194e+18,
|
| 4 |
+
"train_loss": 0.4137112680814314,
|
| 5 |
+
"train_runtime": 1023.9197,
|
| 6 |
+
"train_samples_per_second": 28.006,
|
| 7 |
+
"train_steps_per_second": 1.754
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1255 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.07266250252723694,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-flowers102/checkpoint-1300",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 1796,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"learning_rate": 0.00019888641425389755,
|
| 14 |
+
"loss": 4.5016,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.04,
|
| 19 |
+
"learning_rate": 0.00019777282850779511,
|
| 20 |
+
"loss": 4.311,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07,
|
| 25 |
+
"learning_rate": 0.00019665924276169265,
|
| 26 |
+
"loss": 4.1383,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.09,
|
| 31 |
+
"learning_rate": 0.0001955456570155902,
|
| 32 |
+
"loss": 3.8337,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.11,
|
| 37 |
+
"learning_rate": 0.00019443207126948776,
|
| 38 |
+
"loss": 3.6639,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.13,
|
| 43 |
+
"learning_rate": 0.00019331848552338533,
|
| 44 |
+
"loss": 3.4038,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.16,
|
| 49 |
+
"learning_rate": 0.00019220489977728286,
|
| 50 |
+
"loss": 3.2495,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.18,
|
| 55 |
+
"learning_rate": 0.0001910913140311804,
|
| 56 |
+
"loss": 2.9898,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.2,
|
| 61 |
+
"learning_rate": 0.00018997772828507797,
|
| 62 |
+
"loss": 2.8136,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.22,
|
| 67 |
+
"learning_rate": 0.0001888641425389755,
|
| 68 |
+
"loss": 2.5779,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.22,
|
| 73 |
+
"eval_accuracy": 0.7774509803921569,
|
| 74 |
+
"eval_loss": 2.8894846439361572,
|
| 75 |
+
"eval_runtime": 16.9816,
|
| 76 |
+
"eval_samples_per_second": 60.065,
|
| 77 |
+
"eval_steps_per_second": 7.538,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.24,
|
| 82 |
+
"learning_rate": 0.00018775055679287305,
|
| 83 |
+
"loss": 2.4361,
|
| 84 |
+
"step": 110
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.27,
|
| 88 |
+
"learning_rate": 0.00018663697104677061,
|
| 89 |
+
"loss": 2.2851,
|
| 90 |
+
"step": 120
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.29,
|
| 94 |
+
"learning_rate": 0.00018552338530066815,
|
| 95 |
+
"loss": 2.1522,
|
| 96 |
+
"step": 130
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.31,
|
| 100 |
+
"learning_rate": 0.00018440979955456572,
|
| 101 |
+
"loss": 2.0138,
|
| 102 |
+
"step": 140
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.33,
|
| 106 |
+
"learning_rate": 0.00018329621380846326,
|
| 107 |
+
"loss": 1.878,
|
| 108 |
+
"step": 150
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.36,
|
| 112 |
+
"learning_rate": 0.00018218262806236082,
|
| 113 |
+
"loss": 1.7814,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.38,
|
| 118 |
+
"learning_rate": 0.00018106904231625836,
|
| 119 |
+
"loss": 1.5264,
|
| 120 |
+
"step": 170
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.4,
|
| 124 |
+
"learning_rate": 0.0001799554565701559,
|
| 125 |
+
"loss": 1.5172,
|
| 126 |
+
"step": 180
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.42,
|
| 130 |
+
"learning_rate": 0.00017884187082405347,
|
| 131 |
+
"loss": 1.4431,
|
| 132 |
+
"step": 190
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.45,
|
| 136 |
+
"learning_rate": 0.000177728285077951,
|
| 137 |
+
"loss": 1.2226,
|
| 138 |
+
"step": 200
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.45,
|
| 142 |
+
"eval_accuracy": 0.9254901960784314,
|
| 143 |
+
"eval_loss": 1.5941656827926636,
|
| 144 |
+
"eval_runtime": 16.7137,
|
| 145 |
+
"eval_samples_per_second": 61.028,
|
| 146 |
+
"eval_steps_per_second": 7.658,
|
| 147 |
+
"step": 200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.47,
|
| 151 |
+
"learning_rate": 0.00017661469933184855,
|
| 152 |
+
"loss": 1.2047,
|
| 153 |
+
"step": 210
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.49,
|
| 157 |
+
"learning_rate": 0.00017550111358574611,
|
| 158 |
+
"loss": 1.2643,
|
| 159 |
+
"step": 220
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.51,
|
| 163 |
+
"learning_rate": 0.00017438752783964368,
|
| 164 |
+
"loss": 1.1202,
|
| 165 |
+
"step": 230
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.53,
|
| 169 |
+
"learning_rate": 0.00017327394209354122,
|
| 170 |
+
"loss": 0.9402,
|
| 171 |
+
"step": 240
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.56,
|
| 175 |
+
"learning_rate": 0.00017216035634743876,
|
| 176 |
+
"loss": 0.8425,
|
| 177 |
+
"step": 250
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.58,
|
| 181 |
+
"learning_rate": 0.00017104677060133632,
|
| 182 |
+
"loss": 0.7436,
|
| 183 |
+
"step": 260
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.6,
|
| 187 |
+
"learning_rate": 0.00016993318485523386,
|
| 188 |
+
"loss": 0.6685,
|
| 189 |
+
"step": 270
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.62,
|
| 193 |
+
"learning_rate": 0.0001688195991091314,
|
| 194 |
+
"loss": 0.6464,
|
| 195 |
+
"step": 280
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.65,
|
| 199 |
+
"learning_rate": 0.00016770601336302897,
|
| 200 |
+
"loss": 0.5846,
|
| 201 |
+
"step": 290
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.67,
|
| 205 |
+
"learning_rate": 0.0001665924276169265,
|
| 206 |
+
"loss": 0.606,
|
| 207 |
+
"step": 300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.67,
|
| 211 |
+
"eval_accuracy": 0.9529411764705882,
|
| 212 |
+
"eval_loss": 0.8011782169342041,
|
| 213 |
+
"eval_runtime": 17.625,
|
| 214 |
+
"eval_samples_per_second": 57.872,
|
| 215 |
+
"eval_steps_per_second": 7.262,
|
| 216 |
+
"step": 300
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.69,
|
| 220 |
+
"learning_rate": 0.00016547884187082405,
|
| 221 |
+
"loss": 0.5889,
|
| 222 |
+
"step": 310
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.71,
|
| 226 |
+
"learning_rate": 0.0001643652561247216,
|
| 227 |
+
"loss": 0.5238,
|
| 228 |
+
"step": 320
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.73,
|
| 232 |
+
"learning_rate": 0.0001633630289532294,
|
| 233 |
+
"loss": 0.5481,
|
| 234 |
+
"step": 330
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.76,
|
| 238 |
+
"learning_rate": 0.00016224944320712695,
|
| 239 |
+
"loss": 0.5891,
|
| 240 |
+
"step": 340
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.78,
|
| 244 |
+
"learning_rate": 0.00016113585746102451,
|
| 245 |
+
"loss": 0.4343,
|
| 246 |
+
"step": 350
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.8,
|
| 250 |
+
"learning_rate": 0.00016002227171492205,
|
| 251 |
+
"loss": 0.4681,
|
| 252 |
+
"step": 360
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.82,
|
| 256 |
+
"learning_rate": 0.0001589086859688196,
|
| 257 |
+
"loss": 0.4484,
|
| 258 |
+
"step": 370
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.85,
|
| 262 |
+
"learning_rate": 0.00015779510022271716,
|
| 263 |
+
"loss": 0.3993,
|
| 264 |
+
"step": 380
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.87,
|
| 268 |
+
"learning_rate": 0.0001566815144766147,
|
| 269 |
+
"loss": 0.4087,
|
| 270 |
+
"step": 390
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.89,
|
| 274 |
+
"learning_rate": 0.00015556792873051224,
|
| 275 |
+
"loss": 0.3413,
|
| 276 |
+
"step": 400
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.89,
|
| 280 |
+
"eval_accuracy": 0.9705882352941176,
|
| 281 |
+
"eval_loss": 0.4845229685306549,
|
| 282 |
+
"eval_runtime": 16.4436,
|
| 283 |
+
"eval_samples_per_second": 62.03,
|
| 284 |
+
"eval_steps_per_second": 7.784,
|
| 285 |
+
"step": 400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.91,
|
| 289 |
+
"learning_rate": 0.0001544543429844098,
|
| 290 |
+
"loss": 0.3052,
|
| 291 |
+
"step": 410
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.94,
|
| 295 |
+
"learning_rate": 0.00015334075723830737,
|
| 296 |
+
"loss": 0.2869,
|
| 297 |
+
"step": 420
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.96,
|
| 301 |
+
"learning_rate": 0.0001522271714922049,
|
| 302 |
+
"loss": 0.3613,
|
| 303 |
+
"step": 430
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.98,
|
| 307 |
+
"learning_rate": 0.00015111358574610245,
|
| 308 |
+
"loss": 0.3189,
|
| 309 |
+
"step": 440
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.0,
|
| 313 |
+
"learning_rate": 0.00015000000000000001,
|
| 314 |
+
"loss": 0.2199,
|
| 315 |
+
"step": 450
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.02,
|
| 319 |
+
"learning_rate": 0.00014888641425389755,
|
| 320 |
+
"loss": 0.1689,
|
| 321 |
+
"step": 460
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.05,
|
| 325 |
+
"learning_rate": 0.0001477728285077951,
|
| 326 |
+
"loss": 0.2321,
|
| 327 |
+
"step": 470
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.07,
|
| 331 |
+
"learning_rate": 0.00014665924276169266,
|
| 332 |
+
"loss": 0.1722,
|
| 333 |
+
"step": 480
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.09,
|
| 337 |
+
"learning_rate": 0.0001455456570155902,
|
| 338 |
+
"loss": 0.1581,
|
| 339 |
+
"step": 490
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.11,
|
| 343 |
+
"learning_rate": 0.00014443207126948776,
|
| 344 |
+
"loss": 0.1571,
|
| 345 |
+
"step": 500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.11,
|
| 349 |
+
"eval_accuracy": 0.9813725490196078,
|
| 350 |
+
"eval_loss": 0.26114311814308167,
|
| 351 |
+
"eval_runtime": 18.4125,
|
| 352 |
+
"eval_samples_per_second": 55.397,
|
| 353 |
+
"eval_steps_per_second": 6.952,
|
| 354 |
+
"step": 500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.14,
|
| 358 |
+
"learning_rate": 0.0001433184855233853,
|
| 359 |
+
"loss": 0.1276,
|
| 360 |
+
"step": 510
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.16,
|
| 364 |
+
"learning_rate": 0.00014220489977728287,
|
| 365 |
+
"loss": 0.1203,
|
| 366 |
+
"step": 520
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.18,
|
| 370 |
+
"learning_rate": 0.0001410913140311804,
|
| 371 |
+
"loss": 0.1005,
|
| 372 |
+
"step": 530
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.2,
|
| 376 |
+
"learning_rate": 0.00013997772828507795,
|
| 377 |
+
"loss": 0.1351,
|
| 378 |
+
"step": 540
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.22,
|
| 382 |
+
"learning_rate": 0.0001388641425389755,
|
| 383 |
+
"loss": 0.0928,
|
| 384 |
+
"step": 550
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.25,
|
| 388 |
+
"learning_rate": 0.00013775055679287305,
|
| 389 |
+
"loss": 0.0848,
|
| 390 |
+
"step": 560
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.27,
|
| 394 |
+
"learning_rate": 0.0001366369710467706,
|
| 395 |
+
"loss": 0.1251,
|
| 396 |
+
"step": 570
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.29,
|
| 400 |
+
"learning_rate": 0.00013552338530066816,
|
| 401 |
+
"loss": 0.0774,
|
| 402 |
+
"step": 580
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.31,
|
| 406 |
+
"learning_rate": 0.00013440979955456572,
|
| 407 |
+
"loss": 0.097,
|
| 408 |
+
"step": 590
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.34,
|
| 412 |
+
"learning_rate": 0.00013329621380846326,
|
| 413 |
+
"loss": 0.1237,
|
| 414 |
+
"step": 600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.34,
|
| 418 |
+
"eval_accuracy": 0.9784313725490196,
|
| 419 |
+
"eval_loss": 0.16912123560905457,
|
| 420 |
+
"eval_runtime": 16.6514,
|
| 421 |
+
"eval_samples_per_second": 61.256,
|
| 422 |
+
"eval_steps_per_second": 7.687,
|
| 423 |
+
"step": 600
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.36,
|
| 427 |
+
"learning_rate": 0.0001321826280623608,
|
| 428 |
+
"loss": 0.0724,
|
| 429 |
+
"step": 610
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.38,
|
| 433 |
+
"learning_rate": 0.00013106904231625837,
|
| 434 |
+
"loss": 0.0754,
|
| 435 |
+
"step": 620
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.4,
|
| 439 |
+
"learning_rate": 0.0001299554565701559,
|
| 440 |
+
"loss": 0.065,
|
| 441 |
+
"step": 630
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.43,
|
| 445 |
+
"learning_rate": 0.00012884187082405345,
|
| 446 |
+
"loss": 0.0679,
|
| 447 |
+
"step": 640
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.45,
|
| 451 |
+
"learning_rate": 0.000127728285077951,
|
| 452 |
+
"loss": 0.0579,
|
| 453 |
+
"step": 650
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.47,
|
| 457 |
+
"learning_rate": 0.00012661469933184855,
|
| 458 |
+
"loss": 0.0524,
|
| 459 |
+
"step": 660
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.49,
|
| 463 |
+
"learning_rate": 0.0001255011135857461,
|
| 464 |
+
"loss": 0.0727,
|
| 465 |
+
"step": 670
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.51,
|
| 469 |
+
"learning_rate": 0.00012438752783964366,
|
| 470 |
+
"loss": 0.0721,
|
| 471 |
+
"step": 680
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.54,
|
| 475 |
+
"learning_rate": 0.00012327394209354122,
|
| 476 |
+
"loss": 0.0665,
|
| 477 |
+
"step": 690
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.56,
|
| 481 |
+
"learning_rate": 0.00012216035634743876,
|
| 482 |
+
"loss": 0.049,
|
| 483 |
+
"step": 700
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.56,
|
| 487 |
+
"eval_accuracy": 0.9892156862745098,
|
| 488 |
+
"eval_loss": 0.11457555741071701,
|
| 489 |
+
"eval_runtime": 16.6002,
|
| 490 |
+
"eval_samples_per_second": 61.445,
|
| 491 |
+
"eval_steps_per_second": 7.711,
|
| 492 |
+
"step": 700
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.58,
|
| 496 |
+
"learning_rate": 0.00012104677060133632,
|
| 497 |
+
"loss": 0.0695,
|
| 498 |
+
"step": 710
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.6,
|
| 502 |
+
"learning_rate": 0.00011993318485523385,
|
| 503 |
+
"loss": 0.0487,
|
| 504 |
+
"step": 720
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.63,
|
| 508 |
+
"learning_rate": 0.00011881959910913141,
|
| 509 |
+
"loss": 0.0432,
|
| 510 |
+
"step": 730
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.65,
|
| 514 |
+
"learning_rate": 0.00011770601336302896,
|
| 515 |
+
"loss": 0.0509,
|
| 516 |
+
"step": 740
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.67,
|
| 520 |
+
"learning_rate": 0.0001165924276169265,
|
| 521 |
+
"loss": 0.1105,
|
| 522 |
+
"step": 750
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.69,
|
| 526 |
+
"learning_rate": 0.00011547884187082405,
|
| 527 |
+
"loss": 0.0894,
|
| 528 |
+
"step": 760
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.71,
|
| 532 |
+
"learning_rate": 0.0001143652561247216,
|
| 533 |
+
"loss": 0.0668,
|
| 534 |
+
"step": 770
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.74,
|
| 538 |
+
"learning_rate": 0.00011325167037861917,
|
| 539 |
+
"loss": 0.0663,
|
| 540 |
+
"step": 780
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.76,
|
| 544 |
+
"learning_rate": 0.00011213808463251671,
|
| 545 |
+
"loss": 0.0423,
|
| 546 |
+
"step": 790
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.78,
|
| 550 |
+
"learning_rate": 0.00011102449888641426,
|
| 551 |
+
"loss": 0.0763,
|
| 552 |
+
"step": 800
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.78,
|
| 556 |
+
"eval_accuracy": 0.9862745098039216,
|
| 557 |
+
"eval_loss": 0.12085805088281631,
|
| 558 |
+
"eval_runtime": 17.6825,
|
| 559 |
+
"eval_samples_per_second": 57.684,
|
| 560 |
+
"eval_steps_per_second": 7.239,
|
| 561 |
+
"step": 800
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.8,
|
| 565 |
+
"learning_rate": 0.00010991091314031181,
|
| 566 |
+
"loss": 0.0545,
|
| 567 |
+
"step": 810
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.83,
|
| 571 |
+
"learning_rate": 0.00010879732739420935,
|
| 572 |
+
"loss": 0.0563,
|
| 573 |
+
"step": 820
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.85,
|
| 577 |
+
"learning_rate": 0.0001076837416481069,
|
| 578 |
+
"loss": 0.0743,
|
| 579 |
+
"step": 830
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.87,
|
| 583 |
+
"learning_rate": 0.00010657015590200446,
|
| 584 |
+
"loss": 0.04,
|
| 585 |
+
"step": 840
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.89,
|
| 589 |
+
"learning_rate": 0.000105456570155902,
|
| 590 |
+
"loss": 0.1064,
|
| 591 |
+
"step": 850
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.92,
|
| 595 |
+
"learning_rate": 0.00010434298440979955,
|
| 596 |
+
"loss": 0.0389,
|
| 597 |
+
"step": 860
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.94,
|
| 601 |
+
"learning_rate": 0.00010322939866369712,
|
| 602 |
+
"loss": 0.0372,
|
| 603 |
+
"step": 870
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.96,
|
| 607 |
+
"learning_rate": 0.00010211581291759467,
|
| 608 |
+
"loss": 0.0514,
|
| 609 |
+
"step": 880
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.98,
|
| 613 |
+
"learning_rate": 0.00010100222717149221,
|
| 614 |
+
"loss": 0.0406,
|
| 615 |
+
"step": 890
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.0,
|
| 619 |
+
"learning_rate": 9.988864142538976e-05,
|
| 620 |
+
"loss": 0.0864,
|
| 621 |
+
"step": 900
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.0,
|
| 625 |
+
"eval_accuracy": 0.9803921568627451,
|
| 626 |
+
"eval_loss": 0.12226687371730804,
|
| 627 |
+
"eval_runtime": 16.7815,
|
| 628 |
+
"eval_samples_per_second": 60.781,
|
| 629 |
+
"eval_steps_per_second": 7.627,
|
| 630 |
+
"step": 900
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.03,
|
| 634 |
+
"learning_rate": 9.877505567928731e-05,
|
| 635 |
+
"loss": 0.0337,
|
| 636 |
+
"step": 910
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 2.05,
|
| 640 |
+
"learning_rate": 9.766146993318485e-05,
|
| 641 |
+
"loss": 0.055,
|
| 642 |
+
"step": 920
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.07,
|
| 646 |
+
"learning_rate": 9.65478841870824e-05,
|
| 647 |
+
"loss": 0.0329,
|
| 648 |
+
"step": 930
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.09,
|
| 652 |
+
"learning_rate": 9.543429844097996e-05,
|
| 653 |
+
"loss": 0.028,
|
| 654 |
+
"step": 940
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 2.12,
|
| 658 |
+
"learning_rate": 9.432071269487751e-05,
|
| 659 |
+
"loss": 0.0314,
|
| 660 |
+
"step": 950
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 2.14,
|
| 664 |
+
"learning_rate": 9.320712694877506e-05,
|
| 665 |
+
"loss": 0.0515,
|
| 666 |
+
"step": 960
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 2.16,
|
| 670 |
+
"learning_rate": 9.20935412026726e-05,
|
| 671 |
+
"loss": 0.0294,
|
| 672 |
+
"step": 970
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.18,
|
| 676 |
+
"learning_rate": 9.097995545657017e-05,
|
| 677 |
+
"loss": 0.0318,
|
| 678 |
+
"step": 980
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.2,
|
| 682 |
+
"learning_rate": 8.986636971046771e-05,
|
| 683 |
+
"loss": 0.0332,
|
| 684 |
+
"step": 990
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.23,
|
| 688 |
+
"learning_rate": 8.875278396436526e-05,
|
| 689 |
+
"loss": 0.0786,
|
| 690 |
+
"step": 1000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.23,
|
| 694 |
+
"eval_accuracy": 0.9833333333333333,
|
| 695 |
+
"eval_loss": 0.1075347512960434,
|
| 696 |
+
"eval_runtime": 17.0089,
|
| 697 |
+
"eval_samples_per_second": 59.969,
|
| 698 |
+
"eval_steps_per_second": 7.525,
|
| 699 |
+
"step": 1000
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.25,
|
| 703 |
+
"learning_rate": 8.763919821826281e-05,
|
| 704 |
+
"loss": 0.0269,
|
| 705 |
+
"step": 1010
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.27,
|
| 709 |
+
"learning_rate": 8.652561247216035e-05,
|
| 710 |
+
"loss": 0.0247,
|
| 711 |
+
"step": 1020
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.29,
|
| 715 |
+
"learning_rate": 8.541202672605792e-05,
|
| 716 |
+
"loss": 0.0234,
|
| 717 |
+
"step": 1030
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.32,
|
| 721 |
+
"learning_rate": 8.429844097995546e-05,
|
| 722 |
+
"loss": 0.0241,
|
| 723 |
+
"step": 1040
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.34,
|
| 727 |
+
"learning_rate": 8.318485523385301e-05,
|
| 728 |
+
"loss": 0.0227,
|
| 729 |
+
"step": 1050
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.36,
|
| 733 |
+
"learning_rate": 8.207126948775056e-05,
|
| 734 |
+
"loss": 0.0199,
|
| 735 |
+
"step": 1060
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.38,
|
| 739 |
+
"learning_rate": 8.095768374164812e-05,
|
| 740 |
+
"loss": 0.023,
|
| 741 |
+
"step": 1070
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.41,
|
| 745 |
+
"learning_rate": 7.984409799554567e-05,
|
| 746 |
+
"loss": 0.0254,
|
| 747 |
+
"step": 1080
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.43,
|
| 751 |
+
"learning_rate": 7.873051224944321e-05,
|
| 752 |
+
"loss": 0.0209,
|
| 753 |
+
"step": 1090
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.45,
|
| 757 |
+
"learning_rate": 7.761692650334076e-05,
|
| 758 |
+
"loss": 0.0269,
|
| 759 |
+
"step": 1100
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.45,
|
| 763 |
+
"eval_accuracy": 0.984313725490196,
|
| 764 |
+
"eval_loss": 0.09193924814462662,
|
| 765 |
+
"eval_runtime": 17.7915,
|
| 766 |
+
"eval_samples_per_second": 57.331,
|
| 767 |
+
"eval_steps_per_second": 7.194,
|
| 768 |
+
"step": 1100
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.47,
|
| 772 |
+
"learning_rate": 7.650334075723831e-05,
|
| 773 |
+
"loss": 0.0207,
|
| 774 |
+
"step": 1110
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.49,
|
| 778 |
+
"learning_rate": 7.538975501113587e-05,
|
| 779 |
+
"loss": 0.0189,
|
| 780 |
+
"step": 1120
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 2.52,
|
| 784 |
+
"learning_rate": 7.427616926503342e-05,
|
| 785 |
+
"loss": 0.0213,
|
| 786 |
+
"step": 1130
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 2.54,
|
| 790 |
+
"learning_rate": 7.316258351893096e-05,
|
| 791 |
+
"loss": 0.02,
|
| 792 |
+
"step": 1140
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.56,
|
| 796 |
+
"learning_rate": 7.204899777282851e-05,
|
| 797 |
+
"loss": 0.0683,
|
| 798 |
+
"step": 1150
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.58,
|
| 802 |
+
"learning_rate": 7.093541202672605e-05,
|
| 803 |
+
"loss": 0.0187,
|
| 804 |
+
"step": 1160
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 2.61,
|
| 808 |
+
"learning_rate": 6.982182628062362e-05,
|
| 809 |
+
"loss": 0.0209,
|
| 810 |
+
"step": 1170
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.63,
|
| 814 |
+
"learning_rate": 6.870824053452117e-05,
|
| 815 |
+
"loss": 0.0176,
|
| 816 |
+
"step": 1180
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.65,
|
| 820 |
+
"learning_rate": 6.759465478841871e-05,
|
| 821 |
+
"loss": 0.0199,
|
| 822 |
+
"step": 1190
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 2.67,
|
| 826 |
+
"learning_rate": 6.648106904231626e-05,
|
| 827 |
+
"loss": 0.0178,
|
| 828 |
+
"step": 1200
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 2.67,
|
| 832 |
+
"eval_accuracy": 0.9872549019607844,
|
| 833 |
+
"eval_loss": 0.07947444170713425,
|
| 834 |
+
"eval_runtime": 17.2701,
|
| 835 |
+
"eval_samples_per_second": 59.062,
|
| 836 |
+
"eval_steps_per_second": 7.412,
|
| 837 |
+
"step": 1200
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.69,
|
| 841 |
+
"learning_rate": 6.536748329621381e-05,
|
| 842 |
+
"loss": 0.0184,
|
| 843 |
+
"step": 1210
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.72,
|
| 847 |
+
"learning_rate": 6.425389755011137e-05,
|
| 848 |
+
"loss": 0.0182,
|
| 849 |
+
"step": 1220
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.74,
|
| 853 |
+
"learning_rate": 6.314031180400892e-05,
|
| 854 |
+
"loss": 0.0169,
|
| 855 |
+
"step": 1230
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.76,
|
| 859 |
+
"learning_rate": 6.202672605790646e-05,
|
| 860 |
+
"loss": 0.0169,
|
| 861 |
+
"step": 1240
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.78,
|
| 865 |
+
"learning_rate": 6.091314031180401e-05,
|
| 866 |
+
"loss": 0.0172,
|
| 867 |
+
"step": 1250
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.81,
|
| 871 |
+
"learning_rate": 5.979955456570156e-05,
|
| 872 |
+
"loss": 0.0189,
|
| 873 |
+
"step": 1260
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.83,
|
| 877 |
+
"learning_rate": 5.8685968819599115e-05,
|
| 878 |
+
"loss": 0.0194,
|
| 879 |
+
"step": 1270
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.85,
|
| 883 |
+
"learning_rate": 5.757238307349666e-05,
|
| 884 |
+
"loss": 0.0167,
|
| 885 |
+
"step": 1280
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.87,
|
| 889 |
+
"learning_rate": 5.6458797327394206e-05,
|
| 890 |
+
"loss": 0.0177,
|
| 891 |
+
"step": 1290
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.9,
|
| 895 |
+
"learning_rate": 5.5345211581291766e-05,
|
| 896 |
+
"loss": 0.0165,
|
| 897 |
+
"step": 1300
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.9,
|
| 901 |
+
"eval_accuracy": 0.9872549019607844,
|
| 902 |
+
"eval_loss": 0.07266250252723694,
|
| 903 |
+
"eval_runtime": 16.2341,
|
| 904 |
+
"eval_samples_per_second": 62.831,
|
| 905 |
+
"eval_steps_per_second": 7.885,
|
| 906 |
+
"step": 1300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.92,
|
| 910 |
+
"learning_rate": 5.423162583518931e-05,
|
| 911 |
+
"loss": 0.0165,
|
| 912 |
+
"step": 1310
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 2.94,
|
| 916 |
+
"learning_rate": 5.3118040089086864e-05,
|
| 917 |
+
"loss": 0.0165,
|
| 918 |
+
"step": 1320
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.96,
|
| 922 |
+
"learning_rate": 5.200445434298441e-05,
|
| 923 |
+
"loss": 0.0158,
|
| 924 |
+
"step": 1330
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.98,
|
| 928 |
+
"learning_rate": 5.0890868596881956e-05,
|
| 929 |
+
"loss": 0.0155,
|
| 930 |
+
"step": 1340
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 3.01,
|
| 934 |
+
"learning_rate": 4.977728285077951e-05,
|
| 935 |
+
"loss": 0.0143,
|
| 936 |
+
"step": 1350
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 3.03,
|
| 940 |
+
"learning_rate": 4.866369710467706e-05,
|
| 941 |
+
"loss": 0.0142,
|
| 942 |
+
"step": 1360
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 3.05,
|
| 946 |
+
"learning_rate": 4.7550111358574614e-05,
|
| 947 |
+
"loss": 0.0144,
|
| 948 |
+
"step": 1370
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 3.07,
|
| 952 |
+
"learning_rate": 4.643652561247217e-05,
|
| 953 |
+
"loss": 0.0139,
|
| 954 |
+
"step": 1380
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 3.1,
|
| 958 |
+
"learning_rate": 4.532293986636971e-05,
|
| 959 |
+
"loss": 0.0148,
|
| 960 |
+
"step": 1390
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 3.12,
|
| 964 |
+
"learning_rate": 4.420935412026726e-05,
|
| 965 |
+
"loss": 0.0144,
|
| 966 |
+
"step": 1400
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 3.12,
|
| 970 |
+
"eval_accuracy": 0.9852941176470589,
|
| 971 |
+
"eval_loss": 0.07835763692855835,
|
| 972 |
+
"eval_runtime": 17.268,
|
| 973 |
+
"eval_samples_per_second": 59.069,
|
| 974 |
+
"eval_steps_per_second": 7.413,
|
| 975 |
+
"step": 1400
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 3.14,
|
| 979 |
+
"learning_rate": 4.309576837416481e-05,
|
| 980 |
+
"loss": 0.0138,
|
| 981 |
+
"step": 1410
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 3.16,
|
| 985 |
+
"learning_rate": 4.1982182628062364e-05,
|
| 986 |
+
"loss": 0.0146,
|
| 987 |
+
"step": 1420
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 3.18,
|
| 991 |
+
"learning_rate": 4.0868596881959917e-05,
|
| 992 |
+
"loss": 0.015,
|
| 993 |
+
"step": 1430
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.21,
|
| 997 |
+
"learning_rate": 3.975501113585746e-05,
|
| 998 |
+
"loss": 0.0148,
|
| 999 |
+
"step": 1440
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 3.23,
|
| 1003 |
+
"learning_rate": 3.8641425389755015e-05,
|
| 1004 |
+
"loss": 0.0144,
|
| 1005 |
+
"step": 1450
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 3.25,
|
| 1009 |
+
"learning_rate": 3.752783964365256e-05,
|
| 1010 |
+
"loss": 0.0149,
|
| 1011 |
+
"step": 1460
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 3.27,
|
| 1015 |
+
"learning_rate": 3.6414253897550114e-05,
|
| 1016 |
+
"loss": 0.0134,
|
| 1017 |
+
"step": 1470
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 3.3,
|
| 1021 |
+
"learning_rate": 3.5300668151447666e-05,
|
| 1022 |
+
"loss": 0.0141,
|
| 1023 |
+
"step": 1480
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 3.32,
|
| 1027 |
+
"learning_rate": 3.418708240534521e-05,
|
| 1028 |
+
"loss": 0.0488,
|
| 1029 |
+
"step": 1490
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 3.34,
|
| 1033 |
+
"learning_rate": 3.3073496659242765e-05,
|
| 1034 |
+
"loss": 0.0138,
|
| 1035 |
+
"step": 1500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 3.34,
|
| 1039 |
+
"eval_accuracy": 0.9852941176470589,
|
| 1040 |
+
"eval_loss": 0.07589561492204666,
|
| 1041 |
+
"eval_runtime": 16.5936,
|
| 1042 |
+
"eval_samples_per_second": 61.47,
|
| 1043 |
+
"eval_steps_per_second": 7.714,
|
| 1044 |
+
"step": 1500
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 3.36,
|
| 1048 |
+
"learning_rate": 3.195991091314031e-05,
|
| 1049 |
+
"loss": 0.0142,
|
| 1050 |
+
"step": 1510
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 3.39,
|
| 1054 |
+
"learning_rate": 3.084632516703786e-05,
|
| 1055 |
+
"loss": 0.013,
|
| 1056 |
+
"step": 1520
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 3.41,
|
| 1060 |
+
"learning_rate": 2.9732739420935413e-05,
|
| 1061 |
+
"loss": 0.0138,
|
| 1062 |
+
"step": 1530
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 3.43,
|
| 1066 |
+
"learning_rate": 2.8619153674832965e-05,
|
| 1067 |
+
"loss": 0.0141,
|
| 1068 |
+
"step": 1540
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 3.45,
|
| 1072 |
+
"learning_rate": 2.7505567928730515e-05,
|
| 1073 |
+
"loss": 0.014,
|
| 1074 |
+
"step": 1550
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 3.47,
|
| 1078 |
+
"learning_rate": 2.639198218262806e-05,
|
| 1079 |
+
"loss": 0.0136,
|
| 1080 |
+
"step": 1560
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 3.5,
|
| 1084 |
+
"learning_rate": 2.5278396436525613e-05,
|
| 1085 |
+
"loss": 0.0133,
|
| 1086 |
+
"step": 1570
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 3.52,
|
| 1090 |
+
"learning_rate": 2.4164810690423166e-05,
|
| 1091 |
+
"loss": 0.015,
|
| 1092 |
+
"step": 1580
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 3.54,
|
| 1096 |
+
"learning_rate": 2.3051224944320715e-05,
|
| 1097 |
+
"loss": 0.013,
|
| 1098 |
+
"step": 1590
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 3.56,
|
| 1102 |
+
"learning_rate": 2.1937639198218264e-05,
|
| 1103 |
+
"loss": 0.0135,
|
| 1104 |
+
"step": 1600
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 3.56,
|
| 1108 |
+
"eval_accuracy": 0.9862745098039216,
|
| 1109 |
+
"eval_loss": 0.07374249398708344,
|
| 1110 |
+
"eval_runtime": 16.5728,
|
| 1111 |
+
"eval_samples_per_second": 61.546,
|
| 1112 |
+
"eval_steps_per_second": 7.723,
|
| 1113 |
+
"step": 1600
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 3.59,
|
| 1117 |
+
"learning_rate": 2.0824053452115813e-05,
|
| 1118 |
+
"loss": 0.0134,
|
| 1119 |
+
"step": 1610
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 3.61,
|
| 1123 |
+
"learning_rate": 1.9710467706013363e-05,
|
| 1124 |
+
"loss": 0.0132,
|
| 1125 |
+
"step": 1620
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 3.63,
|
| 1129 |
+
"learning_rate": 1.8596881959910915e-05,
|
| 1130 |
+
"loss": 0.0121,
|
| 1131 |
+
"step": 1630
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 3.65,
|
| 1135 |
+
"learning_rate": 1.7483296213808465e-05,
|
| 1136 |
+
"loss": 0.033,
|
| 1137 |
+
"step": 1640
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 3.67,
|
| 1141 |
+
"learning_rate": 1.6369710467706014e-05,
|
| 1142 |
+
"loss": 0.0378,
|
| 1143 |
+
"step": 1650
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 3.7,
|
| 1147 |
+
"learning_rate": 1.5256124721603565e-05,
|
| 1148 |
+
"loss": 0.0123,
|
| 1149 |
+
"step": 1660
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 3.72,
|
| 1153 |
+
"learning_rate": 1.4142538975501116e-05,
|
| 1154 |
+
"loss": 0.0138,
|
| 1155 |
+
"step": 1670
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 3.74,
|
| 1159 |
+
"learning_rate": 1.3028953229398663e-05,
|
| 1160 |
+
"loss": 0.0124,
|
| 1161 |
+
"step": 1680
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 3.76,
|
| 1165 |
+
"learning_rate": 1.1915367483296214e-05,
|
| 1166 |
+
"loss": 0.0128,
|
| 1167 |
+
"step": 1690
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 3.79,
|
| 1171 |
+
"learning_rate": 1.0801781737193764e-05,
|
| 1172 |
+
"loss": 0.0123,
|
| 1173 |
+
"step": 1700
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 3.79,
|
| 1177 |
+
"eval_accuracy": 0.9852941176470589,
|
| 1178 |
+
"eval_loss": 0.07696886360645294,
|
| 1179 |
+
"eval_runtime": 17.0943,
|
| 1180 |
+
"eval_samples_per_second": 59.669,
|
| 1181 |
+
"eval_steps_per_second": 7.488,
|
| 1182 |
+
"step": 1700
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 3.81,
|
| 1186 |
+
"learning_rate": 9.688195991091315e-06,
|
| 1187 |
+
"loss": 0.0133,
|
| 1188 |
+
"step": 1710
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 3.83,
|
| 1192 |
+
"learning_rate": 8.574610244988866e-06,
|
| 1193 |
+
"loss": 0.013,
|
| 1194 |
+
"step": 1720
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 3.85,
|
| 1198 |
+
"learning_rate": 7.461024498886416e-06,
|
| 1199 |
+
"loss": 0.0122,
|
| 1200 |
+
"step": 1730
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 3.88,
|
| 1204 |
+
"learning_rate": 6.347438752783964e-06,
|
| 1205 |
+
"loss": 0.0124,
|
| 1206 |
+
"step": 1740
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 3.9,
|
| 1210 |
+
"learning_rate": 5.233853006681515e-06,
|
| 1211 |
+
"loss": 0.0117,
|
| 1212 |
+
"step": 1750
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 3.92,
|
| 1216 |
+
"learning_rate": 4.120267260579064e-06,
|
| 1217 |
+
"loss": 0.0116,
|
| 1218 |
+
"step": 1760
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 3.94,
|
| 1222 |
+
"learning_rate": 3.006681514476615e-06,
|
| 1223 |
+
"loss": 0.0122,
|
| 1224 |
+
"step": 1770
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 3.96,
|
| 1228 |
+
"learning_rate": 1.893095768374165e-06,
|
| 1229 |
+
"loss": 0.0123,
|
| 1230 |
+
"step": 1780
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 3.99,
|
| 1234 |
+
"learning_rate": 7.79510022271715e-07,
|
| 1235 |
+
"loss": 0.0132,
|
| 1236 |
+
"step": 1790
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 4.0,
|
| 1240 |
+
"step": 1796,
|
| 1241 |
+
"total_flos": 2.2241519461722194e+18,
|
| 1242 |
+
"train_loss": 0.4137112680814314,
|
| 1243 |
+
"train_runtime": 1023.9197,
|
| 1244 |
+
"train_samples_per_second": 28.006,
|
| 1245 |
+
"train_steps_per_second": 1.754
|
| 1246 |
+
}
|
| 1247 |
+
],
|
| 1248 |
+
"logging_steps": 10,
|
| 1249 |
+
"max_steps": 1796,
|
| 1250 |
+
"num_train_epochs": 4,
|
| 1251 |
+
"save_steps": 100,
|
| 1252 |
+
"total_flos": 2.2241519461722194e+18,
|
| 1253 |
+
"trial_name": null,
|
| 1254 |
+
"trial_params": null
|
| 1255 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbc5a42612cc0512831f6c5854487b16c569cf613638852dc60841dc4a4dd3f6
|
| 3 |
+
size 4600
|