init
Browse files- README.md +77 -0
- all_results.json +12 -0
- config.json +228 -0
- eval_results.json +8 -0
- preprocessor_config.json +17 -0
- train_results.json +7 -0
- trainer_state.json +958 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- food101
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model_index:
|
| 10 |
+
- name: food101_outputs
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Image Classification
|
| 14 |
+
type: image-classification
|
| 15 |
+
dataset:
|
| 16 |
+
name: nateraw/food101
|
| 17 |
+
type: food101
|
| 18 |
+
args: default
|
| 19 |
+
metric:
|
| 20 |
+
name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.8912871287128713
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# food101_outputs
|
| 29 |
+
|
| 30 |
+
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 nateraw/food101 dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.4501
|
| 33 |
+
- Accuracy: 0.8913
|
| 34 |
+
|
| 35 |
+
## Model description
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training and evaluation data
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training procedure
|
| 48 |
+
|
| 49 |
+
### Training hyperparameters
|
| 50 |
+
|
| 51 |
+
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 0.0002
|
| 53 |
+
- train_batch_size: 128
|
| 54 |
+
- eval_batch_size: 128
|
| 55 |
+
- seed: 1337
|
| 56 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 57 |
+
- lr_scheduler_type: linear
|
| 58 |
+
- num_epochs: 5.0
|
| 59 |
+
- mixed_precision_training: Native AMP
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 64 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 65 |
+
| 0.8271 | 1.0 | 592 | 0.6070 | 0.8562 |
|
| 66 |
+
| 0.4376 | 2.0 | 1184 | 0.4947 | 0.8691 |
|
| 67 |
+
| 0.2089 | 3.0 | 1776 | 0.4876 | 0.8747 |
|
| 68 |
+
| 0.0882 | 4.0 | 2368 | 0.4639 | 0.8857 |
|
| 69 |
+
| 0.0452 | 5.0 | 2960 | 0.4501 | 0.8913 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.9.0.dev0
|
| 75 |
+
- Pytorch 1.9.0+cu102
|
| 76 |
+
- Datasets 1.9.1.dev0
|
| 77 |
+
- Tokenizers 0.10.3
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.8912871287128713,
|
| 4 |
+
"eval_loss": 0.45006364583969116,
|
| 5 |
+
"eval_runtime": 107.735,
|
| 6 |
+
"eval_samples_per_second": 234.371,
|
| 7 |
+
"eval_steps_per_second": 1.838,
|
| 8 |
+
"train_loss": 0.48942885282071863,
|
| 9 |
+
"train_runtime": 2221.2523,
|
| 10 |
+
"train_samples_per_second": 170.512,
|
| 11 |
+
"train_steps_per_second": 1.333
|
| 12 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"finetuning_task": "image-classification",
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "apple_pie",
|
| 13 |
+
"1": "baby_back_ribs",
|
| 14 |
+
"10": "bruschetta",
|
| 15 |
+
"100": "waffles",
|
| 16 |
+
"11": "caesar_salad",
|
| 17 |
+
"12": "cannoli",
|
| 18 |
+
"13": "caprese_salad",
|
| 19 |
+
"14": "carrot_cake",
|
| 20 |
+
"15": "ceviche",
|
| 21 |
+
"16": "cheese_plate",
|
| 22 |
+
"17": "cheesecake",
|
| 23 |
+
"18": "chicken_curry",
|
| 24 |
+
"19": "chicken_quesadilla",
|
| 25 |
+
"2": "baklava",
|
| 26 |
+
"20": "chicken_wings",
|
| 27 |
+
"21": "chocolate_cake",
|
| 28 |
+
"22": "chocolate_mousse",
|
| 29 |
+
"23": "churros",
|
| 30 |
+
"24": "clam_chowder",
|
| 31 |
+
"25": "club_sandwich",
|
| 32 |
+
"26": "crab_cakes",
|
| 33 |
+
"27": "creme_brulee",
|
| 34 |
+
"28": "croque_madame",
|
| 35 |
+
"29": "cup_cakes",
|
| 36 |
+
"3": "beef_carpaccio",
|
| 37 |
+
"30": "deviled_eggs",
|
| 38 |
+
"31": "donuts",
|
| 39 |
+
"32": "dumplings",
|
| 40 |
+
"33": "edamame",
|
| 41 |
+
"34": "eggs_benedict",
|
| 42 |
+
"35": "escargots",
|
| 43 |
+
"36": "falafel",
|
| 44 |
+
"37": "filet_mignon",
|
| 45 |
+
"38": "fish_and_chips",
|
| 46 |
+
"39": "foie_gras",
|
| 47 |
+
"4": "beef_tartare",
|
| 48 |
+
"40": "french_fries",
|
| 49 |
+
"41": "french_onion_soup",
|
| 50 |
+
"42": "french_toast",
|
| 51 |
+
"43": "fried_calamari",
|
| 52 |
+
"44": "fried_rice",
|
| 53 |
+
"45": "frozen_yogurt",
|
| 54 |
+
"46": "garlic_bread",
|
| 55 |
+
"47": "gnocchi",
|
| 56 |
+
"48": "greek_salad",
|
| 57 |
+
"49": "grilled_cheese_sandwich",
|
| 58 |
+
"5": "beet_salad",
|
| 59 |
+
"50": "grilled_salmon",
|
| 60 |
+
"51": "guacamole",
|
| 61 |
+
"52": "gyoza",
|
| 62 |
+
"53": "hamburger",
|
| 63 |
+
"54": "hot_and_sour_soup",
|
| 64 |
+
"55": "hot_dog",
|
| 65 |
+
"56": "huevos_rancheros",
|
| 66 |
+
"57": "hummus",
|
| 67 |
+
"58": "ice_cream",
|
| 68 |
+
"59": "lasagna",
|
| 69 |
+
"6": "beignets",
|
| 70 |
+
"60": "lobster_bisque",
|
| 71 |
+
"61": "lobster_roll_sandwich",
|
| 72 |
+
"62": "macaroni_and_cheese",
|
| 73 |
+
"63": "macarons",
|
| 74 |
+
"64": "miso_soup",
|
| 75 |
+
"65": "mussels",
|
| 76 |
+
"66": "nachos",
|
| 77 |
+
"67": "omelette",
|
| 78 |
+
"68": "onion_rings",
|
| 79 |
+
"69": "oysters",
|
| 80 |
+
"7": "bibimbap",
|
| 81 |
+
"70": "pad_thai",
|
| 82 |
+
"71": "paella",
|
| 83 |
+
"72": "pancakes",
|
| 84 |
+
"73": "panna_cotta",
|
| 85 |
+
"74": "peking_duck",
|
| 86 |
+
"75": "pho",
|
| 87 |
+
"76": "pizza",
|
| 88 |
+
"77": "pork_chop",
|
| 89 |
+
"78": "poutine",
|
| 90 |
+
"79": "prime_rib",
|
| 91 |
+
"8": "bread_pudding",
|
| 92 |
+
"80": "pulled_pork_sandwich",
|
| 93 |
+
"81": "ramen",
|
| 94 |
+
"82": "ravioli",
|
| 95 |
+
"83": "red_velvet_cake",
|
| 96 |
+
"84": "risotto",
|
| 97 |
+
"85": "samosa",
|
| 98 |
+
"86": "sashimi",
|
| 99 |
+
"87": "scallops",
|
| 100 |
+
"88": "seaweed_salad",
|
| 101 |
+
"89": "shrimp_and_grits",
|
| 102 |
+
"9": "breakfast_burrito",
|
| 103 |
+
"90": "spaghetti_bolognese",
|
| 104 |
+
"91": "spaghetti_carbonara",
|
| 105 |
+
"92": "spring_rolls",
|
| 106 |
+
"93": "steak",
|
| 107 |
+
"94": "strawberry_shortcake",
|
| 108 |
+
"95": "sushi",
|
| 109 |
+
"96": "tacos",
|
| 110 |
+
"97": "takoyaki",
|
| 111 |
+
"98": "tiramisu",
|
| 112 |
+
"99": "tuna_tartare"
|
| 113 |
+
},
|
| 114 |
+
"image_size": 224,
|
| 115 |
+
"initializer_range": 0.02,
|
| 116 |
+
"intermediate_size": 3072,
|
| 117 |
+
"label2id": {
|
| 118 |
+
"apple_pie": "0",
|
| 119 |
+
"baby_back_ribs": "1",
|
| 120 |
+
"baklava": "2",
|
| 121 |
+
"beef_carpaccio": "3",
|
| 122 |
+
"beef_tartare": "4",
|
| 123 |
+
"beet_salad": "5",
|
| 124 |
+
"beignets": "6",
|
| 125 |
+
"bibimbap": "7",
|
| 126 |
+
"bread_pudding": "8",
|
| 127 |
+
"breakfast_burrito": "9",
|
| 128 |
+
"bruschetta": "10",
|
| 129 |
+
"caesar_salad": "11",
|
| 130 |
+
"cannoli": "12",
|
| 131 |
+
"caprese_salad": "13",
|
| 132 |
+
"carrot_cake": "14",
|
| 133 |
+
"ceviche": "15",
|
| 134 |
+
"cheese_plate": "16",
|
| 135 |
+
"cheesecake": "17",
|
| 136 |
+
"chicken_curry": "18",
|
| 137 |
+
"chicken_quesadilla": "19",
|
| 138 |
+
"chicken_wings": "20",
|
| 139 |
+
"chocolate_cake": "21",
|
| 140 |
+
"chocolate_mousse": "22",
|
| 141 |
+
"churros": "23",
|
| 142 |
+
"clam_chowder": "24",
|
| 143 |
+
"club_sandwich": "25",
|
| 144 |
+
"crab_cakes": "26",
|
| 145 |
+
"creme_brulee": "27",
|
| 146 |
+
"croque_madame": "28",
|
| 147 |
+
"cup_cakes": "29",
|
| 148 |
+
"deviled_eggs": "30",
|
| 149 |
+
"donuts": "31",
|
| 150 |
+
"dumplings": "32",
|
| 151 |
+
"edamame": "33",
|
| 152 |
+
"eggs_benedict": "34",
|
| 153 |
+
"escargots": "35",
|
| 154 |
+
"falafel": "36",
|
| 155 |
+
"filet_mignon": "37",
|
| 156 |
+
"fish_and_chips": "38",
|
| 157 |
+
"foie_gras": "39",
|
| 158 |
+
"french_fries": "40",
|
| 159 |
+
"french_onion_soup": "41",
|
| 160 |
+
"french_toast": "42",
|
| 161 |
+
"fried_calamari": "43",
|
| 162 |
+
"fried_rice": "44",
|
| 163 |
+
"frozen_yogurt": "45",
|
| 164 |
+
"garlic_bread": "46",
|
| 165 |
+
"gnocchi": "47",
|
| 166 |
+
"greek_salad": "48",
|
| 167 |
+
"grilled_cheese_sandwich": "49",
|
| 168 |
+
"grilled_salmon": "50",
|
| 169 |
+
"guacamole": "51",
|
| 170 |
+
"gyoza": "52",
|
| 171 |
+
"hamburger": "53",
|
| 172 |
+
"hot_and_sour_soup": "54",
|
| 173 |
+
"hot_dog": "55",
|
| 174 |
+
"huevos_rancheros": "56",
|
| 175 |
+
"hummus": "57",
|
| 176 |
+
"ice_cream": "58",
|
| 177 |
+
"lasagna": "59",
|
| 178 |
+
"lobster_bisque": "60",
|
| 179 |
+
"lobster_roll_sandwich": "61",
|
| 180 |
+
"macaroni_and_cheese": "62",
|
| 181 |
+
"macarons": "63",
|
| 182 |
+
"miso_soup": "64",
|
| 183 |
+
"mussels": "65",
|
| 184 |
+
"nachos": "66",
|
| 185 |
+
"omelette": "67",
|
| 186 |
+
"onion_rings": "68",
|
| 187 |
+
"oysters": "69",
|
| 188 |
+
"pad_thai": "70",
|
| 189 |
+
"paella": "71",
|
| 190 |
+
"pancakes": "72",
|
| 191 |
+
"panna_cotta": "73",
|
| 192 |
+
"peking_duck": "74",
|
| 193 |
+
"pho": "75",
|
| 194 |
+
"pizza": "76",
|
| 195 |
+
"pork_chop": "77",
|
| 196 |
+
"poutine": "78",
|
| 197 |
+
"prime_rib": "79",
|
| 198 |
+
"pulled_pork_sandwich": "80",
|
| 199 |
+
"ramen": "81",
|
| 200 |
+
"ravioli": "82",
|
| 201 |
+
"red_velvet_cake": "83",
|
| 202 |
+
"risotto": "84",
|
| 203 |
+
"samosa": "85",
|
| 204 |
+
"sashimi": "86",
|
| 205 |
+
"scallops": "87",
|
| 206 |
+
"seaweed_salad": "88",
|
| 207 |
+
"shrimp_and_grits": "89",
|
| 208 |
+
"spaghetti_bolognese": "90",
|
| 209 |
+
"spaghetti_carbonara": "91",
|
| 210 |
+
"spring_rolls": "92",
|
| 211 |
+
"steak": "93",
|
| 212 |
+
"strawberry_shortcake": "94",
|
| 213 |
+
"sushi": "95",
|
| 214 |
+
"tacos": "96",
|
| 215 |
+
"takoyaki": "97",
|
| 216 |
+
"tiramisu": "98",
|
| 217 |
+
"tuna_tartare": "99",
|
| 218 |
+
"waffles": "100"
|
| 219 |
+
},
|
| 220 |
+
"layer_norm_eps": 1e-12,
|
| 221 |
+
"model_type": "vit",
|
| 222 |
+
"num_attention_heads": 12,
|
| 223 |
+
"num_channels": 3,
|
| 224 |
+
"num_hidden_layers": 12,
|
| 225 |
+
"patch_size": 16,
|
| 226 |
+
"torch_dtype": "float32",
|
| 227 |
+
"transformers_version": "4.9.0.dev0"
|
| 228 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.8912871287128713,
|
| 4 |
+
"eval_loss": 0.45006364583969116,
|
| 5 |
+
"eval_runtime": 107.735,
|
| 6 |
+
"eval_samples_per_second": 234.371,
|
| 7 |
+
"eval_steps_per_second": 1.838
|
| 8 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_resize": true,
|
| 4 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_std": [
|
| 11 |
+
0.5,
|
| 12 |
+
0.5,
|
| 13 |
+
0.5
|
| 14 |
+
],
|
| 15 |
+
"resample": 2,
|
| 16 |
+
"size": 224
|
| 17 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.48942885282071863,
|
| 4 |
+
"train_runtime": 2221.2523,
|
| 5 |
+
"train_samples_per_second": 170.512,
|
| 6 |
+
"train_steps_per_second": 1.333
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,958 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8912871287128713,
|
| 3 |
+
"best_model_checkpoint": "food101_outputs/checkpoint-2960",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 2960,
|
| 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": 0.00019864864864864865,
|
| 13 |
+
"loss": 4.4083,
|
| 14 |
+
"step": 20
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"learning_rate": 0.0001972972972972973,
|
| 19 |
+
"loss": 3.884,
|
| 20 |
+
"step": 40
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.1,
|
| 24 |
+
"learning_rate": 0.00019594594594594594,
|
| 25 |
+
"loss": 3.4068,
|
| 26 |
+
"step": 60
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.14,
|
| 30 |
+
"learning_rate": 0.00019459459459459462,
|
| 31 |
+
"loss": 2.9784,
|
| 32 |
+
"step": 80
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.17,
|
| 36 |
+
"learning_rate": 0.00019324324324324326,
|
| 37 |
+
"loss": 2.6549,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.2,
|
| 42 |
+
"learning_rate": 0.0001918918918918919,
|
| 43 |
+
"loss": 2.3437,
|
| 44 |
+
"step": 120
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"learning_rate": 0.00019054054054054055,
|
| 49 |
+
"loss": 2.1107,
|
| 50 |
+
"step": 140
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.27,
|
| 54 |
+
"learning_rate": 0.0001891891891891892,
|
| 55 |
+
"loss": 1.8803,
|
| 56 |
+
"step": 160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.3,
|
| 60 |
+
"learning_rate": 0.00018783783783783784,
|
| 61 |
+
"loss": 1.7025,
|
| 62 |
+
"step": 180
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.34,
|
| 66 |
+
"learning_rate": 0.0001864864864864865,
|
| 67 |
+
"loss": 1.5403,
|
| 68 |
+
"step": 200
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.37,
|
| 72 |
+
"learning_rate": 0.00018513513513513513,
|
| 73 |
+
"loss": 1.48,
|
| 74 |
+
"step": 220
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.41,
|
| 78 |
+
"learning_rate": 0.0001837837837837838,
|
| 79 |
+
"loss": 1.358,
|
| 80 |
+
"step": 240
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.44,
|
| 84 |
+
"learning_rate": 0.00018243243243243245,
|
| 85 |
+
"loss": 1.2943,
|
| 86 |
+
"step": 260
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.47,
|
| 90 |
+
"learning_rate": 0.0001810810810810811,
|
| 91 |
+
"loss": 1.2301,
|
| 92 |
+
"step": 280
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.51,
|
| 96 |
+
"learning_rate": 0.00017972972972972974,
|
| 97 |
+
"loss": 1.1578,
|
| 98 |
+
"step": 300
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.54,
|
| 102 |
+
"learning_rate": 0.00017837837837837839,
|
| 103 |
+
"loss": 1.0811,
|
| 104 |
+
"step": 320
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.57,
|
| 108 |
+
"learning_rate": 0.00017702702702702703,
|
| 109 |
+
"loss": 1.0662,
|
| 110 |
+
"step": 340
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.61,
|
| 114 |
+
"learning_rate": 0.00017567567567567568,
|
| 115 |
+
"loss": 1.0146,
|
| 116 |
+
"step": 360
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.64,
|
| 120 |
+
"learning_rate": 0.00017432432432432432,
|
| 121 |
+
"loss": 0.9584,
|
| 122 |
+
"step": 380
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.68,
|
| 126 |
+
"learning_rate": 0.000172972972972973,
|
| 127 |
+
"loss": 0.973,
|
| 128 |
+
"step": 400
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.71,
|
| 132 |
+
"learning_rate": 0.00017162162162162164,
|
| 133 |
+
"loss": 0.9817,
|
| 134 |
+
"step": 420
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.74,
|
| 138 |
+
"learning_rate": 0.00017027027027027028,
|
| 139 |
+
"loss": 0.9552,
|
| 140 |
+
"step": 440
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.78,
|
| 144 |
+
"learning_rate": 0.00016891891891891893,
|
| 145 |
+
"loss": 0.916,
|
| 146 |
+
"step": 460
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.81,
|
| 150 |
+
"learning_rate": 0.00016756756756756757,
|
| 151 |
+
"loss": 0.8896,
|
| 152 |
+
"step": 480
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.84,
|
| 156 |
+
"learning_rate": 0.00016621621621621622,
|
| 157 |
+
"loss": 0.8855,
|
| 158 |
+
"step": 500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.88,
|
| 162 |
+
"learning_rate": 0.00016486486486486486,
|
| 163 |
+
"loss": 0.8823,
|
| 164 |
+
"step": 520
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.91,
|
| 168 |
+
"learning_rate": 0.0001635135135135135,
|
| 169 |
+
"loss": 0.8059,
|
| 170 |
+
"step": 540
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.95,
|
| 174 |
+
"learning_rate": 0.00016216216216216218,
|
| 175 |
+
"loss": 0.8323,
|
| 176 |
+
"step": 560
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.98,
|
| 180 |
+
"learning_rate": 0.00016081081081081083,
|
| 181 |
+
"loss": 0.8271,
|
| 182 |
+
"step": 580
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.0,
|
| 186 |
+
"eval_accuracy": 0.8561584158415841,
|
| 187 |
+
"eval_loss": 0.6070069074630737,
|
| 188 |
+
"eval_runtime": 142.5311,
|
| 189 |
+
"eval_samples_per_second": 177.154,
|
| 190 |
+
"eval_steps_per_second": 1.389,
|
| 191 |
+
"step": 592
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.01,
|
| 195 |
+
"learning_rate": 0.00015945945945945947,
|
| 196 |
+
"loss": 0.6876,
|
| 197 |
+
"step": 600
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.05,
|
| 201 |
+
"learning_rate": 0.00015810810810810812,
|
| 202 |
+
"loss": 0.4771,
|
| 203 |
+
"step": 620
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.08,
|
| 207 |
+
"learning_rate": 0.00015675675675675676,
|
| 208 |
+
"loss": 0.4998,
|
| 209 |
+
"step": 640
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.11,
|
| 213 |
+
"learning_rate": 0.0001554054054054054,
|
| 214 |
+
"loss": 0.4753,
|
| 215 |
+
"step": 660
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.15,
|
| 219 |
+
"learning_rate": 0.00015405405405405405,
|
| 220 |
+
"loss": 0.5197,
|
| 221 |
+
"step": 680
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.18,
|
| 225 |
+
"learning_rate": 0.0001527027027027027,
|
| 226 |
+
"loss": 0.527,
|
| 227 |
+
"step": 700
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.22,
|
| 231 |
+
"learning_rate": 0.00015135135135135137,
|
| 232 |
+
"loss": 0.5371,
|
| 233 |
+
"step": 720
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.25,
|
| 237 |
+
"learning_rate": 0.00015000000000000001,
|
| 238 |
+
"loss": 0.4992,
|
| 239 |
+
"step": 740
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.28,
|
| 243 |
+
"learning_rate": 0.00014864864864864866,
|
| 244 |
+
"loss": 0.4728,
|
| 245 |
+
"step": 760
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 1.32,
|
| 249 |
+
"learning_rate": 0.0001472972972972973,
|
| 250 |
+
"loss": 0.5185,
|
| 251 |
+
"step": 780
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 1.35,
|
| 255 |
+
"learning_rate": 0.00014594594594594595,
|
| 256 |
+
"loss": 0.5071,
|
| 257 |
+
"step": 800
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.39,
|
| 261 |
+
"learning_rate": 0.00014459459459459462,
|
| 262 |
+
"loss": 0.4728,
|
| 263 |
+
"step": 820
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.42,
|
| 267 |
+
"learning_rate": 0.00014324324324324324,
|
| 268 |
+
"loss": 0.4731,
|
| 269 |
+
"step": 840
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.45,
|
| 273 |
+
"learning_rate": 0.00014189189189189188,
|
| 274 |
+
"loss": 0.5211,
|
| 275 |
+
"step": 860
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.49,
|
| 279 |
+
"learning_rate": 0.00014054054054054056,
|
| 280 |
+
"loss": 0.4949,
|
| 281 |
+
"step": 880
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.52,
|
| 285 |
+
"learning_rate": 0.0001391891891891892,
|
| 286 |
+
"loss": 0.4847,
|
| 287 |
+
"step": 900
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 1.55,
|
| 291 |
+
"learning_rate": 0.00013783783783783785,
|
| 292 |
+
"loss": 0.4626,
|
| 293 |
+
"step": 920
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.59,
|
| 297 |
+
"learning_rate": 0.0001364864864864865,
|
| 298 |
+
"loss": 0.456,
|
| 299 |
+
"step": 940
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.62,
|
| 303 |
+
"learning_rate": 0.00013513513513513514,
|
| 304 |
+
"loss": 0.4938,
|
| 305 |
+
"step": 960
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.66,
|
| 309 |
+
"learning_rate": 0.0001337837837837838,
|
| 310 |
+
"loss": 0.4846,
|
| 311 |
+
"step": 980
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.69,
|
| 315 |
+
"learning_rate": 0.00013243243243243243,
|
| 316 |
+
"loss": 0.4576,
|
| 317 |
+
"step": 1000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.72,
|
| 321 |
+
"learning_rate": 0.00013108108108108107,
|
| 322 |
+
"loss": 0.4766,
|
| 323 |
+
"step": 1020
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.76,
|
| 327 |
+
"learning_rate": 0.00012972972972972974,
|
| 328 |
+
"loss": 0.4741,
|
| 329 |
+
"step": 1040
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.79,
|
| 333 |
+
"learning_rate": 0.0001283783783783784,
|
| 334 |
+
"loss": 0.4225,
|
| 335 |
+
"step": 1060
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 1.82,
|
| 339 |
+
"learning_rate": 0.00012702702702702703,
|
| 340 |
+
"loss": 0.4201,
|
| 341 |
+
"step": 1080
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 1.86,
|
| 345 |
+
"learning_rate": 0.00012567567567567568,
|
| 346 |
+
"loss": 0.4327,
|
| 347 |
+
"step": 1100
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.89,
|
| 351 |
+
"learning_rate": 0.00012432432432432433,
|
| 352 |
+
"loss": 0.4771,
|
| 353 |
+
"step": 1120
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.93,
|
| 357 |
+
"learning_rate": 0.000122972972972973,
|
| 358 |
+
"loss": 0.4473,
|
| 359 |
+
"step": 1140
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.96,
|
| 363 |
+
"learning_rate": 0.00012162162162162163,
|
| 364 |
+
"loss": 0.4569,
|
| 365 |
+
"step": 1160
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 1.99,
|
| 369 |
+
"learning_rate": 0.00012027027027027027,
|
| 370 |
+
"loss": 0.4376,
|
| 371 |
+
"step": 1180
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.0,
|
| 375 |
+
"eval_accuracy": 0.8691485148514851,
|
| 376 |
+
"eval_loss": 0.4947212338447571,
|
| 377 |
+
"eval_runtime": 107.3521,
|
| 378 |
+
"eval_samples_per_second": 235.207,
|
| 379 |
+
"eval_steps_per_second": 1.844,
|
| 380 |
+
"step": 1184
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.03,
|
| 384 |
+
"learning_rate": 0.00011891891891891893,
|
| 385 |
+
"loss": 0.2526,
|
| 386 |
+
"step": 1200
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 2.06,
|
| 390 |
+
"learning_rate": 0.00011756756756756758,
|
| 391 |
+
"loss": 0.2468,
|
| 392 |
+
"step": 1220
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.09,
|
| 396 |
+
"learning_rate": 0.00011621621621621621,
|
| 397 |
+
"loss": 0.2298,
|
| 398 |
+
"step": 1240
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.13,
|
| 402 |
+
"learning_rate": 0.00011486486486486487,
|
| 403 |
+
"loss": 0.2294,
|
| 404 |
+
"step": 1260
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.16,
|
| 408 |
+
"learning_rate": 0.00011351351351351351,
|
| 409 |
+
"loss": 0.2408,
|
| 410 |
+
"step": 1280
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.2,
|
| 414 |
+
"learning_rate": 0.00011216216216216217,
|
| 415 |
+
"loss": 0.2245,
|
| 416 |
+
"step": 1300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 2.23,
|
| 420 |
+
"learning_rate": 0.00011081081081081082,
|
| 421 |
+
"loss": 0.2391,
|
| 422 |
+
"step": 1320
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.26,
|
| 426 |
+
"learning_rate": 0.00010945945945945946,
|
| 427 |
+
"loss": 0.241,
|
| 428 |
+
"step": 1340
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.3,
|
| 432 |
+
"learning_rate": 0.00010810810810810812,
|
| 433 |
+
"loss": 0.2197,
|
| 434 |
+
"step": 1360
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.33,
|
| 438 |
+
"learning_rate": 0.00010675675675675677,
|
| 439 |
+
"loss": 0.2467,
|
| 440 |
+
"step": 1380
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.36,
|
| 444 |
+
"learning_rate": 0.0001054054054054054,
|
| 445 |
+
"loss": 0.2397,
|
| 446 |
+
"step": 1400
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.4,
|
| 450 |
+
"learning_rate": 0.00010405405405405406,
|
| 451 |
+
"loss": 0.2308,
|
| 452 |
+
"step": 1420
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.43,
|
| 456 |
+
"learning_rate": 0.0001027027027027027,
|
| 457 |
+
"loss": 0.25,
|
| 458 |
+
"step": 1440
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.47,
|
| 462 |
+
"learning_rate": 0.00010135135135135136,
|
| 463 |
+
"loss": 0.2291,
|
| 464 |
+
"step": 1460
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.5,
|
| 468 |
+
"learning_rate": 0.0001,
|
| 469 |
+
"loss": 0.2496,
|
| 470 |
+
"step": 1480
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.53,
|
| 474 |
+
"learning_rate": 9.864864864864865e-05,
|
| 475 |
+
"loss": 0.2322,
|
| 476 |
+
"step": 1500
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.57,
|
| 480 |
+
"learning_rate": 9.729729729729731e-05,
|
| 481 |
+
"loss": 0.2266,
|
| 482 |
+
"step": 1520
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.6,
|
| 486 |
+
"learning_rate": 9.594594594594595e-05,
|
| 487 |
+
"loss": 0.2201,
|
| 488 |
+
"step": 1540
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.64,
|
| 492 |
+
"learning_rate": 9.45945945945946e-05,
|
| 493 |
+
"loss": 0.2497,
|
| 494 |
+
"step": 1560
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.67,
|
| 498 |
+
"learning_rate": 9.324324324324324e-05,
|
| 499 |
+
"loss": 0.2276,
|
| 500 |
+
"step": 1580
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.7,
|
| 504 |
+
"learning_rate": 9.18918918918919e-05,
|
| 505 |
+
"loss": 0.1945,
|
| 506 |
+
"step": 1600
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.74,
|
| 510 |
+
"learning_rate": 9.054054054054055e-05,
|
| 511 |
+
"loss": 0.2174,
|
| 512 |
+
"step": 1620
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.77,
|
| 516 |
+
"learning_rate": 8.918918918918919e-05,
|
| 517 |
+
"loss": 0.2423,
|
| 518 |
+
"step": 1640
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.8,
|
| 522 |
+
"learning_rate": 8.783783783783784e-05,
|
| 523 |
+
"loss": 0.2242,
|
| 524 |
+
"step": 1660
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.84,
|
| 528 |
+
"learning_rate": 8.64864864864865e-05,
|
| 529 |
+
"loss": 0.2383,
|
| 530 |
+
"step": 1680
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 2.87,
|
| 534 |
+
"learning_rate": 8.513513513513514e-05,
|
| 535 |
+
"loss": 0.2582,
|
| 536 |
+
"step": 1700
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.91,
|
| 540 |
+
"learning_rate": 8.378378378378379e-05,
|
| 541 |
+
"loss": 0.2125,
|
| 542 |
+
"step": 1720
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.94,
|
| 546 |
+
"learning_rate": 8.243243243243243e-05,
|
| 547 |
+
"loss": 0.2307,
|
| 548 |
+
"step": 1740
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.97,
|
| 552 |
+
"learning_rate": 8.108108108108109e-05,
|
| 553 |
+
"loss": 0.2089,
|
| 554 |
+
"step": 1760
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.0,
|
| 558 |
+
"eval_accuracy": 0.8746930693069307,
|
| 559 |
+
"eval_loss": 0.48760801553726196,
|
| 560 |
+
"eval_runtime": 106.972,
|
| 561 |
+
"eval_samples_per_second": 236.043,
|
| 562 |
+
"eval_steps_per_second": 1.851,
|
| 563 |
+
"step": 1776
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 3.01,
|
| 567 |
+
"learning_rate": 7.972972972972974e-05,
|
| 568 |
+
"loss": 0.1821,
|
| 569 |
+
"step": 1780
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.04,
|
| 573 |
+
"learning_rate": 7.837837837837838e-05,
|
| 574 |
+
"loss": 0.1332,
|
| 575 |
+
"step": 1800
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 3.07,
|
| 579 |
+
"learning_rate": 7.702702702702703e-05,
|
| 580 |
+
"loss": 0.116,
|
| 581 |
+
"step": 1820
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 3.11,
|
| 585 |
+
"learning_rate": 7.567567567567568e-05,
|
| 586 |
+
"loss": 0.119,
|
| 587 |
+
"step": 1840
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 3.14,
|
| 591 |
+
"learning_rate": 7.432432432432433e-05,
|
| 592 |
+
"loss": 0.1222,
|
| 593 |
+
"step": 1860
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 3.18,
|
| 597 |
+
"learning_rate": 7.297297297297297e-05,
|
| 598 |
+
"loss": 0.118,
|
| 599 |
+
"step": 1880
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 3.21,
|
| 603 |
+
"learning_rate": 7.162162162162162e-05,
|
| 604 |
+
"loss": 0.1078,
|
| 605 |
+
"step": 1900
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 3.24,
|
| 609 |
+
"learning_rate": 7.027027027027028e-05,
|
| 610 |
+
"loss": 0.0982,
|
| 611 |
+
"step": 1920
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.28,
|
| 615 |
+
"learning_rate": 6.891891891891892e-05,
|
| 616 |
+
"loss": 0.1056,
|
| 617 |
+
"step": 1940
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 3.31,
|
| 621 |
+
"learning_rate": 6.756756756756757e-05,
|
| 622 |
+
"loss": 0.099,
|
| 623 |
+
"step": 1960
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 3.34,
|
| 627 |
+
"learning_rate": 6.621621621621621e-05,
|
| 628 |
+
"loss": 0.0961,
|
| 629 |
+
"step": 1980
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 3.38,
|
| 633 |
+
"learning_rate": 6.486486486486487e-05,
|
| 634 |
+
"loss": 0.1051,
|
| 635 |
+
"step": 2000
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 3.41,
|
| 639 |
+
"learning_rate": 6.358108108108109e-05,
|
| 640 |
+
"loss": 0.1161,
|
| 641 |
+
"step": 2020
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 3.45,
|
| 645 |
+
"learning_rate": 6.222972972972973e-05,
|
| 646 |
+
"loss": 0.0919,
|
| 647 |
+
"step": 2040
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 3.48,
|
| 651 |
+
"learning_rate": 6.087837837837839e-05,
|
| 652 |
+
"loss": 0.1181,
|
| 653 |
+
"step": 2060
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.51,
|
| 657 |
+
"learning_rate": 5.952702702702703e-05,
|
| 658 |
+
"loss": 0.1215,
|
| 659 |
+
"step": 2080
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.55,
|
| 663 |
+
"learning_rate": 5.817567567567568e-05,
|
| 664 |
+
"loss": 0.0959,
|
| 665 |
+
"step": 2100
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 3.58,
|
| 669 |
+
"learning_rate": 5.682432432432433e-05,
|
| 670 |
+
"loss": 0.0866,
|
| 671 |
+
"step": 2120
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 3.61,
|
| 675 |
+
"learning_rate": 5.547297297297298e-05,
|
| 676 |
+
"loss": 0.117,
|
| 677 |
+
"step": 2140
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 3.65,
|
| 681 |
+
"learning_rate": 5.412162162162162e-05,
|
| 682 |
+
"loss": 0.1063,
|
| 683 |
+
"step": 2160
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.68,
|
| 687 |
+
"learning_rate": 5.277027027027027e-05,
|
| 688 |
+
"loss": 0.0993,
|
| 689 |
+
"step": 2180
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.72,
|
| 693 |
+
"learning_rate": 5.1418918918918925e-05,
|
| 694 |
+
"loss": 0.1057,
|
| 695 |
+
"step": 2200
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.75,
|
| 699 |
+
"learning_rate": 5.006756756756758e-05,
|
| 700 |
+
"loss": 0.1194,
|
| 701 |
+
"step": 2220
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 3.78,
|
| 705 |
+
"learning_rate": 4.871621621621622e-05,
|
| 706 |
+
"loss": 0.0929,
|
| 707 |
+
"step": 2240
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 3.82,
|
| 711 |
+
"learning_rate": 4.736486486486487e-05,
|
| 712 |
+
"loss": 0.08,
|
| 713 |
+
"step": 2260
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.85,
|
| 717 |
+
"learning_rate": 4.601351351351352e-05,
|
| 718 |
+
"loss": 0.1133,
|
| 719 |
+
"step": 2280
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 3.89,
|
| 723 |
+
"learning_rate": 4.4662162162162164e-05,
|
| 724 |
+
"loss": 0.0996,
|
| 725 |
+
"step": 2300
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 3.92,
|
| 729 |
+
"learning_rate": 4.3310810810810816e-05,
|
| 730 |
+
"loss": 0.0992,
|
| 731 |
+
"step": 2320
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 3.95,
|
| 735 |
+
"learning_rate": 4.195945945945946e-05,
|
| 736 |
+
"loss": 0.0941,
|
| 737 |
+
"step": 2340
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 3.99,
|
| 741 |
+
"learning_rate": 4.060810810810811e-05,
|
| 742 |
+
"loss": 0.0882,
|
| 743 |
+
"step": 2360
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 4.0,
|
| 747 |
+
"eval_accuracy": 0.8856633663366337,
|
| 748 |
+
"eval_loss": 0.463856965303421,
|
| 749 |
+
"eval_runtime": 107.2753,
|
| 750 |
+
"eval_samples_per_second": 235.376,
|
| 751 |
+
"eval_steps_per_second": 1.846,
|
| 752 |
+
"step": 2368
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 4.02,
|
| 756 |
+
"learning_rate": 3.925675675675676e-05,
|
| 757 |
+
"loss": 0.0796,
|
| 758 |
+
"step": 2380
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 4.05,
|
| 762 |
+
"learning_rate": 3.790540540540541e-05,
|
| 763 |
+
"loss": 0.0353,
|
| 764 |
+
"step": 2400
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 4.09,
|
| 768 |
+
"learning_rate": 3.6554054054054055e-05,
|
| 769 |
+
"loss": 0.0536,
|
| 770 |
+
"step": 2420
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 4.12,
|
| 774 |
+
"learning_rate": 3.520270270270271e-05,
|
| 775 |
+
"loss": 0.0564,
|
| 776 |
+
"step": 2440
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 4.16,
|
| 780 |
+
"learning_rate": 3.385135135135135e-05,
|
| 781 |
+
"loss": 0.0506,
|
| 782 |
+
"step": 2460
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 4.19,
|
| 786 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 787 |
+
"loss": 0.0547,
|
| 788 |
+
"step": 2480
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 4.22,
|
| 792 |
+
"learning_rate": 3.114864864864865e-05,
|
| 793 |
+
"loss": 0.0462,
|
| 794 |
+
"step": 2500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 4.26,
|
| 798 |
+
"learning_rate": 2.97972972972973e-05,
|
| 799 |
+
"loss": 0.0501,
|
| 800 |
+
"step": 2520
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 4.29,
|
| 804 |
+
"learning_rate": 2.8445945945945946e-05,
|
| 805 |
+
"loss": 0.0588,
|
| 806 |
+
"step": 2540
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 4.32,
|
| 810 |
+
"learning_rate": 2.7094594594594598e-05,
|
| 811 |
+
"loss": 0.0303,
|
| 812 |
+
"step": 2560
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 4.36,
|
| 816 |
+
"learning_rate": 2.5743243243243243e-05,
|
| 817 |
+
"loss": 0.0411,
|
| 818 |
+
"step": 2580
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 4.39,
|
| 822 |
+
"learning_rate": 2.4391891891891895e-05,
|
| 823 |
+
"loss": 0.0406,
|
| 824 |
+
"step": 2600
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 4.43,
|
| 828 |
+
"learning_rate": 2.3040540540540543e-05,
|
| 829 |
+
"loss": 0.0378,
|
| 830 |
+
"step": 2620
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 4.46,
|
| 834 |
+
"learning_rate": 2.1689189189189192e-05,
|
| 835 |
+
"loss": 0.0391,
|
| 836 |
+
"step": 2640
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 4.49,
|
| 840 |
+
"learning_rate": 2.033783783783784e-05,
|
| 841 |
+
"loss": 0.038,
|
| 842 |
+
"step": 2660
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 4.53,
|
| 846 |
+
"learning_rate": 1.898648648648649e-05,
|
| 847 |
+
"loss": 0.0443,
|
| 848 |
+
"step": 2680
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 4.56,
|
| 852 |
+
"learning_rate": 1.7635135135135137e-05,
|
| 853 |
+
"loss": 0.0391,
|
| 854 |
+
"step": 2700
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 4.59,
|
| 858 |
+
"learning_rate": 1.6283783783783786e-05,
|
| 859 |
+
"loss": 0.0439,
|
| 860 |
+
"step": 2720
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 4.63,
|
| 864 |
+
"learning_rate": 1.4932432432432433e-05,
|
| 865 |
+
"loss": 0.0532,
|
| 866 |
+
"step": 2740
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 4.66,
|
| 870 |
+
"learning_rate": 1.3581081081081081e-05,
|
| 871 |
+
"loss": 0.0395,
|
| 872 |
+
"step": 2760
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 4.7,
|
| 876 |
+
"learning_rate": 1.222972972972973e-05,
|
| 877 |
+
"loss": 0.0458,
|
| 878 |
+
"step": 2780
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 4.73,
|
| 882 |
+
"learning_rate": 1.0878378378378378e-05,
|
| 883 |
+
"loss": 0.0588,
|
| 884 |
+
"step": 2800
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 4.76,
|
| 888 |
+
"learning_rate": 9.527027027027027e-06,
|
| 889 |
+
"loss": 0.0465,
|
| 890 |
+
"step": 2820
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 4.8,
|
| 894 |
+
"learning_rate": 8.175675675675675e-06,
|
| 895 |
+
"loss": 0.036,
|
| 896 |
+
"step": 2840
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 4.83,
|
| 900 |
+
"learning_rate": 6.8243243243243244e-06,
|
| 901 |
+
"loss": 0.0437,
|
| 902 |
+
"step": 2860
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 4.86,
|
| 906 |
+
"learning_rate": 5.472972972972974e-06,
|
| 907 |
+
"loss": 0.0487,
|
| 908 |
+
"step": 2880
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 4.9,
|
| 912 |
+
"learning_rate": 4.121621621621622e-06,
|
| 913 |
+
"loss": 0.0273,
|
| 914 |
+
"step": 2900
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 4.93,
|
| 918 |
+
"learning_rate": 2.7702702702702708e-06,
|
| 919 |
+
"loss": 0.0392,
|
| 920 |
+
"step": 2920
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 4.97,
|
| 924 |
+
"learning_rate": 1.418918918918919e-06,
|
| 925 |
+
"loss": 0.0458,
|
| 926 |
+
"step": 2940
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 5.0,
|
| 930 |
+
"learning_rate": 6.756756756756757e-08,
|
| 931 |
+
"loss": 0.0452,
|
| 932 |
+
"step": 2960
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 5.0,
|
| 936 |
+
"eval_accuracy": 0.8912871287128713,
|
| 937 |
+
"eval_loss": 0.45006364583969116,
|
| 938 |
+
"eval_runtime": 106.893,
|
| 939 |
+
"eval_samples_per_second": 236.218,
|
| 940 |
+
"eval_steps_per_second": 1.852,
|
| 941 |
+
"step": 2960
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 5.0,
|
| 945 |
+
"step": 2960,
|
| 946 |
+
"total_flos": 0.0,
|
| 947 |
+
"train_loss": 0.48942885282071863,
|
| 948 |
+
"train_runtime": 2221.2523,
|
| 949 |
+
"train_samples_per_second": 170.512,
|
| 950 |
+
"train_steps_per_second": 1.333
|
| 951 |
+
}
|
| 952 |
+
],
|
| 953 |
+
"max_steps": 2960,
|
| 954 |
+
"num_train_epochs": 5,
|
| 955 |
+
"total_flos": 0.0,
|
| 956 |
+
"trial_name": null,
|
| 957 |
+
"trial_params": null
|
| 958 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:854337aa979b4d66fa7b7c37eeeed817ea454fd96fce3eeddd27799e56c2a3d1
|
| 3 |
+
size 2671
|