Overriding config with config/train_shakespeare_char.py:
# train a miniature character-level shakespeare model
# good for debugging and playing on macbooks and such

out_dir = 'out-shakespeare-char'
eval_interval = 250 # keep frequent because we'll overfit
eval_iters = 200
log_interval = 10 # don't print too too often

# we expect to overfit on this small dataset, so only save when val improves
always_save_checkpoint = False

wandb_log = False # override via command line if you like
wandb_project = 'shakespeare-char'
wandb_run_name = 'mini-gpt'

dataset = 'shakespeare_char'
gradient_accumulation_steps = 1
batch_size = 64
block_size = 256 # context of up to 256 previous characters

# baby GPT model :)
n_layer = 6
n_head = 6
n_embd = 384
dropout = 0.2

learning_rate = 1e-3 # with baby networks can afford to go a bit higher
max_iters = 5000
lr_decay_iters = 5000 # make equal to max_iters usually
min_lr = 1e-4 # learning_rate / 10 usually
beta2 = 0.99 # make a bit bigger because number of tokens per iter is small

warmup_iters = 100 # not super necessary potentially

# on macbook also add
# device = 'cpu'  # run on cpu only
# compile = False # do not torch compile the model

Overriding: device = cpu
Overriding: compile = False
Overriding: eval_iters = 20
Overriding: log_interval = 1
Overriding: block_size = 64
Overriding: batch_size = 12
Overriding: n_layer = 4
Overriding: n_head = 4
Overriding: n_embd = 128
Overriding: max_iters = 2000
Overriding: lr_decay_iters = 2000
Overriding: dropout = 0.0
tokens per iteration will be: 768
found vocab_size = 65 (inside data/shakespeare_char/meta.pkl)
Initializing a new model from scratch
number of parameters: 0.80M
num decayed parameter tensors: 18, with 802,944 parameters
num non-decayed parameter tensors: 9, with 1,152 parameters
using fused AdamW: False
step 0: train loss 4.1676, val loss 4.1649
iter 0: loss 4.1828, time 1223.93ms, mfu -100.00%
iter 1: loss 4.1373, time 217.34ms, mfu -100.00%
iter 2: loss 4.1347, time 68.81ms, mfu -100.00%
iter 3: loss 4.0995, time 58.03ms, mfu -100.00%
iter 4: loss 4.0387, time 44.75ms, mfu -100.00%
iter 5: loss 3.9758, time 58.14ms, mfu 0.02%
iter 6: loss 3.9126, time 52.50ms, mfu 0.02%
iter 7: loss 3.8463, time 60.08ms, mfu 0.02%
iter 8: loss 3.8169, time 41.12ms, mfu 0.02%
iter 9: loss 3.7311, time 82.98ms, mfu 0.02%
iter 10: loss 3.7366, time 75.53ms, mfu 0.02%
iter 11: loss 3.7234, time 163.69ms, mfu 0.02%
iter 12: loss 3.7059, time 113.61ms, mfu 0.02%
iter 13: loss 3.6791, time 66.28ms, mfu 0.02%
iter 14: loss 3.6453, time 38.49ms, mfu 0.02%
iter 15: loss 3.6266, time 100.73ms, mfu 0.02%
iter 16: loss 3.6050, time 86.62ms, mfu 0.02%
iter 17: loss 3.6008, time 84.93ms, mfu 0.02%
iter 18: loss 3.6244, time 54.99ms, mfu 0.02%
iter 19: loss 3.6423, time 65.41ms, mfu 0.02%
iter 20: loss 3.5233, time 63.36ms, mfu 0.02%
iter 21: loss 3.5387, time 84.31ms, mfu 0.02%
iter 22: loss 3.4933, time 150.91ms, mfu 0.02%
iter 23: loss 3.4671, time 106.99ms, mfu 0.02%
iter 24: loss 3.4993, time 110.91ms, mfu 0.02%
iter 25: loss 3.3414, time 130.44ms, mfu 0.02%
iter 26: loss 3.3209, time 118.09ms, mfu 0.02%
iter 27: loss 3.3452, time 75.92ms, mfu 0.02%
iter 28: loss 3.2668, time 70.63ms, mfu 0.02%
iter 29: loss 3.2942, time 70.58ms, mfu 0.02%
iter 30: loss 3.3294, time 86.41ms, mfu 0.02%
iter 31: loss 3.2203, time 83.62ms, mfu 0.02%
iter 32: loss 3.1959, time 53.55ms, mfu 0.02%
iter 33: loss 3.2006, time 97.77ms, mfu 0.02%
iter 34: loss 3.1428, time 82.04ms, mfu 0.02%
iter 35: loss 3.2393, time 112.00ms, mfu 0.02%
iter 36: loss 3.1355, time 139.74ms, mfu 0.02%
iter 37: loss 3.1533, time 63.94ms, mfu 0.02%
iter 38: loss 3.0117, time 68.01ms, mfu 0.02%
iter 39: loss 3.0625, time 45.24ms, mfu 0.02%
iter 40: loss 3.0920, time 43.37ms, mfu 0.02%
iter 41: loss 3.0309, time 55.40ms, mfu 0.02%
iter 42: loss 2.9807, time 54.01ms, mfu 0.02%
iter 43: loss 2.9671, time 69.53ms, mfu 0.02%
iter 44: loss 3.0005, time 46.22ms, mfu 0.02%
iter 45: loss 2.9795, time 100.77ms, mfu 0.02%
iter 46: loss 2.9250, time 163.28ms, mfu 0.02%
iter 47: loss 3.0510, time 72.85ms, mfu 0.02%
iter 48: loss 2.9333, time 75.92ms, mfu 0.02%
iter 49: loss 2.9340, time 69.45ms, mfu 0.02%
iter 50: loss 2.9336, time 58.58ms, mfu 0.02%
iter 51: loss 2.9030, time 72.10ms, mfu 0.02%
iter 52: loss 2.9111, time 54.82ms, mfu 0.02%
iter 53: loss 2.8949, time 54.46ms, mfu 0.02%
iter 54: loss 2.8129, time 36.66ms, mfu 0.02%
iter 55: loss 2.8076, time 41.24ms, mfu 0.02%
iter 56: loss 2.7797, time 53.16ms, mfu 0.02%
iter 57: loss 2.8472, time 48.78ms, mfu 0.02%
iter 58: loss 2.8127, time 74.25ms, mfu 0.02%
iter 59: loss 2.8339, time 67.71ms, mfu 0.02%
iter 60: loss 2.7890, time 286.78ms, mfu 0.02%
iter 61: loss 2.8220, time 103.94ms, mfu 0.02%
iter 62: loss 2.7516, time 121.77ms, mfu 0.02%
iter 63: loss 2.7931, time 132.24ms, mfu 0.02%
iter 64: loss 2.7913, time 74.11ms, mfu 0.02%
iter 65: loss 2.7310, time 62.46ms, mfu 0.02%
iter 66: loss 2.7577, time 68.28ms, mfu 0.02%
iter 67: loss 2.7374, time 85.54ms, mfu 0.02%
iter 68: loss 2.7673, time 112.98ms, mfu 0.02%
iter 69: loss 2.7820, time 294.16ms, mfu 0.02%
iter 70: loss 2.7069, time 172.88ms, mfu 0.01%
iter 71: loss 2.7687, time 125.95ms, mfu 0.01%
iter 72: loss 2.6593, time 58.20ms, mfu 0.02%
iter 73: loss 2.7034, time 57.34ms, mfu 0.02%
iter 74: loss 2.6512, time 56.84ms, mfu 0.02%
iter 75: loss 2.7666, time 46.99ms, mfu 0.02%
iter 76: loss 2.6618, time 78.13ms, mfu 0.02%
iter 77: loss 2.7576, time 127.62ms, mfu 0.02%
iter 78: loss 2.6682, time 110.15ms, mfu 0.02%
iter 79: loss 2.6772, time 103.92ms, mfu 0.02%
iter 80: loss 2.6128, time 97.51ms, mfu 0.02%
iter 81: loss 2.6870, time 116.40ms, mfu 0.02%
iter 82: loss 2.6893, time 66.73ms, mfu 0.02%
iter 83: loss 2.6264, time 63.07ms, mfu 0.02%
iter 84: loss 2.7267, time 49.26ms, mfu 0.02%
iter 85: loss 2.6810, time 71.17ms, mfu 0.02%
iter 86: loss 2.5991, time 60.22ms, mfu 0.02%
iter 87: loss 2.6400, time 48.97ms, mfu 0.02%
iter 88: loss 2.6090, time 52.75ms, mfu 0.02%
iter 89: loss 2.7311, time 62.02ms, mfu 0.02%
iter 90: loss 2.6146, time 52.53ms, mfu 0.02%
iter 91: loss 2.6667, time 180.76ms, mfu 0.02%
iter 92: loss 2.6025, time 119.35ms, mfu 0.02%
iter 93: loss 2.5399, time 126.80ms, mfu 0.02%
iter 94: loss 2.7116, time 110.47ms, mfu 0.02%
iter 95: loss 2.6400, time 83.08ms, mfu 0.02%
iter 96: loss 2.6739, time 70.46ms, mfu 0.02%
iter 97: loss 2.5839, time 46.84ms, mfu 0.02%
iter 98: loss 2.5320, time 64.38ms, mfu 0.02%
iter 99: loss 2.6740, time 45.02ms, mfu 0.02%
iter 100: loss 2.6635, time 252.42ms, mfu 0.02%
iter 101: loss 2.6532, time 109.94ms, mfu 0.02%
iter 102: loss 2.5912, time 104.34ms, mfu 0.02%
iter 103: loss 2.6308, time 99.66ms, mfu 0.02%
iter 104: loss 2.5048, time 72.63ms, mfu 0.02%
iter 105: loss 2.5748, time 116.11ms, mfu 0.02%
iter 106: loss 2.5280, time 94.57ms, mfu 0.02%
iter 107: loss 2.5885, time 82.96ms, mfu 0.02%
iter 108: loss 2.5621, time 102.37ms, mfu 0.02%
iter 109: loss 2.5919, time 77.20ms, mfu 0.02%
iter 110: loss 2.5880, time 67.05ms, mfu 0.02%
iter 111: loss 2.5340, time 270.11ms, mfu 0.01%
iter 112: loss 2.5389, time 104.90ms, mfu 0.01%
iter 113: loss 2.5485, time 64.73ms, mfu 0.01%
iter 114: loss 2.6036, time 85.47ms, mfu 0.01%
iter 115: loss 2.5520, time 101.85ms, mfu 0.01%
iter 116: loss 2.5809, time 72.26ms, mfu 0.01%
iter 117: loss 2.5443, time 83.07ms, mfu 0.01%
iter 118: loss 2.5850, time 115.37ms, mfu 0.01%
iter 119: loss 2.6244, time 70.80ms, mfu 0.01%
iter 120: loss 2.6186, time 84.38ms, mfu 0.01%
iter 121: loss 2.7192, time 91.96ms, mfu 0.01%
iter 122: loss 2.6091, time 108.22ms, mfu 0.01%
iter 123: loss 2.5891, time 137.46ms, mfu 0.01%
iter 124: loss 2.6232, time 113.58ms, mfu 0.01%
iter 125: loss 2.5940, time 73.32ms, mfu 0.01%
iter 126: loss 2.6158, time 51.35ms, mfu 0.02%
iter 127: loss 2.6776, time 39.81ms, mfu 0.02%
iter 128: loss 2.5884, time 48.98ms, mfu 0.02%
iter 129: loss 2.5599, time 69.63ms, mfu 0.02%
iter 130: loss 2.5422, time 65.24ms, mfu 0.02%
iter 131: loss 2.6984, time 60.48ms, mfu 0.02%
iter 132: loss 2.5189, time 65.36ms, mfu 0.02%
iter 133: loss 2.5712, time 252.01ms, mfu 0.02%
iter 134: loss 2.4379, time 425.86ms, mfu 0.02%
iter 135: loss 2.5714, time 310.00ms, mfu 0.01%
iter 136: loss 2.5871, time 156.14ms, mfu 0.01%
iter 137: loss 2.5021, time 241.15ms, mfu 0.01%
iter 138: loss 2.5119, time 91.65ms, mfu 0.01%
iter 139: loss 2.5801, time 63.49ms, mfu 0.01%
iter 140: loss 2.4921, time 65.65ms, mfu 0.01%
iter 141: loss 2.5164, time 65.46ms, mfu 0.01%
iter 142: loss 2.5426, time 119.29ms, mfu 0.01%
iter 143: loss 2.5652, time 111.29ms, mfu 0.01%
iter 144: loss 2.5373, time 115.99ms, mfu 0.01%
iter 145: loss 2.5433, time 108.44ms, mfu 0.01%
iter 146: loss 2.5070, time 133.20ms, mfu 0.01%
iter 147: loss 2.5597, time 177.81ms, mfu 0.01%
iter 148: loss 2.4607, time 73.43ms, mfu 0.01%
iter 149: loss 2.5515, time 97.14ms, mfu 0.01%
iter 150: loss 2.5425, time 63.95ms, mfu 0.01%
iter 151: loss 2.5234, time 61.76ms, mfu 0.01%
iter 152: loss 2.5735, time 52.47ms, mfu 0.02%
iter 153: loss 2.4897, time 51.56ms, mfu 0.02%
iter 154: loss 2.4569, time 64.18ms, mfu 0.02%
iter 155: loss 2.4786, time 57.48ms, mfu 0.02%
iter 156: loss 2.5061, time 131.40ms, mfu 0.02%
iter 157: loss 2.5567, time 345.80ms, mfu 0.02%
iter 158: loss 2.5771, time 275.71ms, mfu 0.01%
iter 159: loss 2.5045, time 147.32ms, mfu 0.01%
iter 160: loss 2.5243, time 116.62ms, mfu 0.01%
iter 161: loss 2.4993, time 269.28ms, mfu 0.01%
iter 162: loss 2.4630, time 85.03ms, mfu 0.01%
iter 163: loss 2.4979, time 155.34ms, mfu 0.01%
iter 164: loss 2.5054, time 94.11ms, mfu 0.01%
iter 165: loss 2.6246, time 59.07ms, mfu 0.01%
iter 166: loss 2.5134, time 67.23ms, mfu 0.01%
iter 167: loss 2.4725, time 61.98ms, mfu 0.01%
iter 168: loss 2.5520, time 74.93ms, mfu 0.01%
iter 169: loss 2.4899, time 98.28ms, mfu 0.01%
iter 170: loss 2.4741, time 216.28ms, mfu 0.01%
iter 171: loss 2.3834, time 723.55ms, mfu 0.01%
iter 172: loss 2.5202, time 135.61ms, mfu 0.01%
iter 173: loss 2.5233, time 433.11ms, mfu 0.01%
iter 174: loss 2.4690, time 164.05ms, mfu 0.01%
iter 175: loss 2.4643, time 86.47ms, mfu 0.01%
iter 176: loss 2.4494, time 74.24ms, mfu 0.01%
iter 177: loss 2.4908, time 92.97ms, mfu 0.01%
iter 178: loss 2.4802, time 166.71ms, mfu 0.01%
iter 179: loss 2.6177, time 151.31ms, mfu 0.01%
iter 180: loss 2.4928, time 117.74ms, mfu 0.01%
iter 181: loss 2.4498, time 138.08ms, mfu 0.01%
iter 182: loss 2.4439, time 165.22ms, mfu 0.01%
iter 183: loss 2.5471, time 121.00ms, mfu 0.01%
iter 184: loss 2.4470, time 74.63ms, mfu 0.01%
iter 185: loss 2.5639, time 97.20ms, mfu 0.01%
iter 186: loss 2.5656, time 67.96ms, mfu 0.01%
iter 187: loss 2.5070, time 84.94ms, mfu 0.01%
iter 188: loss 2.4840, time 281.52ms, mfu 0.01%
iter 189: loss 2.5641, time 102.62ms, mfu 0.01%
iter 190: loss 2.5444, time 122.50ms, mfu 0.01%
iter 191: loss 2.5446, time 103.48ms, mfu 0.01%
iter 192: loss 2.4553, time 68.94ms, mfu 0.01%
iter 193: loss 2.5763, time 64.89ms, mfu 0.01%
iter 194: loss 2.4801, time 50.28ms, mfu 0.01%
iter 195: loss 2.4763, time 56.81ms, mfu 0.02%
iter 196: loss 2.4731, time 48.32ms, mfu 0.02%
iter 197: loss 2.4632, time 64.11ms, mfu 0.02%
iter 198: loss 2.4527, time 68.85ms, mfu 0.02%
iter 199: loss 2.4878, time 61.17ms, mfu 0.02%
iter 200: loss 2.5039, time 122.41ms, mfu 0.02%
iter 201: loss 2.4361, time 194.26ms, mfu 0.02%
iter 202: loss 2.4518, time 111.25ms, mfu 0.02%
iter 203: loss 2.5402, time 154.76ms, mfu 0.01%
iter 204: loss 2.4754, time 134.26ms, mfu 0.01%
iter 205: loss 2.4789, time 212.30ms, mfu 0.01%
iter 206: loss 2.4742, time 423.06ms, mfu 0.01%
iter 207: loss 2.5718, time 190.88ms, mfu 0.01%
iter 208: loss 2.3844, time 137.09ms, mfu 0.01%
iter 209: loss 2.5291, time 79.31ms, mfu 0.01%
iter 210: loss 2.4330, time 58.97ms, mfu 0.01%
iter 211: loss 2.5309, time 61.84ms, mfu 0.01%
iter 212: loss 2.4654, time 68.26ms, mfu 0.01%
iter 213: loss 2.4521, time 99.23ms, mfu 0.01%
iter 214: loss 2.5320, time 91.09ms, mfu 0.01%
iter 215: loss 2.5425, time 133.77ms, mfu 0.01%
iter 216: loss 2.5085, time 57.80ms, mfu 0.01%
iter 217: loss 2.4557, time 81.06ms, mfu 0.01%
iter 218: loss 2.5043, time 56.47ms, mfu 0.02%
iter 219: loss 2.4581, time 53.80ms, mfu 0.02%
iter 220: loss 2.4903, time 91.49ms, mfu 0.02%
iter 221: loss 2.5044, time 104.18ms, mfu 0.02%
iter 222: loss 2.4566, time 99.53ms, mfu 0.02%
iter 223: loss 2.5313, time 89.99ms, mfu 0.02%
iter 224: loss 2.3978, time 101.90ms, mfu 0.01%
iter 225: loss 2.5483, time 80.66ms, mfu 0.01%
iter 226: loss 2.4627, time 58.21ms, mfu 0.02%
iter 227: loss 2.4574, time 63.25ms, mfu 0.02%
iter 228: loss 2.4476, time 79.43ms, mfu 0.02%
iter 229: loss 2.5279, time 58.96ms, mfu 0.02%
iter 230: loss 2.4648, time 106.69ms, mfu 0.02%
iter 231: loss 2.4212, time 84.62ms, mfu 0.02%
iter 232: loss 2.4458, time 38.65ms, mfu 0.02%
iter 233: loss 2.4612, time 67.64ms, mfu 0.02%
iter 234: loss 2.4193, time 59.48ms, mfu 0.02%
iter 235: loss 2.4913, time 54.45ms, mfu 0.02%
iter 236: loss 2.4356, time 49.38ms, mfu 0.02%
iter 237: loss 2.4827, time 40.85ms, mfu 0.02%
iter 238: loss 2.5102, time 77.36ms, mfu 0.02%
iter 239: loss 2.4670, time 132.63ms, mfu 0.02%
iter 240: loss 2.5144, time 41.77ms, mfu 0.02%
iter 241: loss 2.4216, time 44.61ms, mfu 0.02%
iter 242: loss 2.4851, time 45.60ms, mfu 0.02%
iter 243: loss 2.4914, time 88.16ms, mfu 0.02%
iter 244: loss 2.4181, time 51.08ms, mfu 0.02%
iter 245: loss 2.5124, time 43.99ms, mfu 0.02%
iter 246: loss 2.4154, time 49.25ms, mfu 0.02%
iter 247: loss 2.4658, time 66.60ms, mfu 0.02%
iter 248: loss 2.4475, time 75.19ms, mfu 0.02%
iter 249: loss 2.4449, time 143.37ms, mfu 0.02%
step 250: train loss 2.4293, val loss 2.4447
saving checkpoint to out-shakespeare-char
iter 250: loss 2.4904, time 1648.82ms, mfu 0.02%
iter 251: loss 2.3638, time 79.29ms, mfu 0.02%
iter 252: loss 2.5004, time 71.86ms, mfu 0.02%
iter 253: loss 2.4087, time 81.23ms, mfu 0.02%
iter 254: loss 2.3968, time 83.31ms, mfu 0.02%
iter 255: loss 2.4558, time 119.26ms, mfu 0.02%
iter 256: loss 2.3588, time 82.72ms, mfu 0.02%
iter 257: loss 2.3921, time 104.92ms, mfu 0.02%
iter 258: loss 2.4123, time 131.47ms, mfu 0.02%
iter 259: loss 2.3825, time 84.24ms, mfu 0.02%
iter 260: loss 2.4461, time 69.63ms, mfu 0.02%
iter 261: loss 2.4801, time 48.21ms, mfu 0.02%
iter 262: loss 2.4433, time 55.20ms, mfu 0.02%
iter 263: loss 2.4063, time 57.25ms, mfu 0.02%
iter 264: loss 2.4662, time 54.31ms, mfu 0.02%
iter 265: loss 2.4957, time 53.75ms, mfu 0.02%
iter 266: loss 2.4313, time 70.65ms, mfu 0.02%
iter 267: loss 2.3545, time 103.97ms, mfu 0.02%
iter 268: loss 2.5298, time 113.85ms, mfu 0.02%
iter 269: loss 2.4722, time 62.42ms, mfu 0.02%
iter 270: loss 2.4044, time 134.79ms, mfu 0.02%
iter 271: loss 2.4732, time 122.70ms, mfu 0.02%
iter 272: loss 2.4242, time 78.72ms, mfu 0.02%
iter 273: loss 2.3979, time 68.63ms, mfu 0.02%
iter 274: loss 2.4059, time 55.59ms, mfu 0.02%
iter 275: loss 2.4296, time 93.06ms, mfu 0.02%
iter 276: loss 2.4052, time 103.94ms, mfu 0.02%
iter 277: loss 2.3876, time 117.45ms, mfu 0.02%
iter 278: loss 2.3873, time 69.46ms, mfu 0.02%
iter 279: loss 2.3665, time 128.88ms, mfu 0.02%
iter 280: loss 2.3788, time 862.69ms, mfu 0.01%
iter 281: loss 2.4736, time 733.35ms, mfu 0.01%
iter 282: loss 2.4060, time 242.35ms, mfu 0.01%
iter 283: loss 2.4246, time 119.86ms, mfu 0.01%
iter 284: loss 2.3952, time 105.30ms, mfu 0.01%
iter 285: loss 2.4339, time 151.03ms, mfu 0.01%
iter 286: loss 2.4566, time 152.71ms, mfu 0.01%
iter 287: loss 2.4284, time 129.52ms, mfu 0.01%
iter 288: loss 2.4340, time 135.87ms, mfu 0.01%
iter 289: loss 2.3849, time 113.75ms, mfu 0.01%
iter 290: loss 2.3959, time 76.86ms, mfu 0.01%
iter 291: loss 2.3171, time 103.21ms, mfu 0.01%
iter 292: loss 2.3974, time 80.63ms, mfu 0.01%
iter 293: loss 2.3744, time 73.59ms, mfu 0.01%
iter 294: loss 2.3162, time 60.55ms, mfu 0.01%
iter 295: loss 2.4403, time 58.87ms, mfu 0.01%
iter 296: loss 2.3260, time 47.47ms, mfu 0.02%
iter 297: loss 2.3889, time 50.10ms, mfu 0.02%
iter 298: loss 2.3428, time 90.50ms, mfu 0.02%
iter 299: loss 2.3893, time 95.81ms, mfu 0.02%
iter 300: loss 2.3350, time 64.14ms, mfu 0.02%
iter 301: loss 2.2811, time 64.79ms, mfu 0.02%
iter 302: loss 2.4488, time 50.28ms, mfu 0.02%
iter 303: loss 2.4061, time 44.49ms, mfu 0.02%
iter 304: loss 2.4852, time 49.56ms, mfu 0.02%
iter 305: loss 2.4113, time 46.92ms, mfu 0.02%
iter 306: loss 2.3722, time 45.57ms, mfu 0.02%
iter 307: loss 2.3499, time 43.77ms, mfu 0.02%
iter 308: loss 2.4330, time 37.07ms, mfu 0.02%
iter 309: loss 2.4252, time 39.45ms, mfu 0.02%
iter 310: loss 2.3489, time 47.92ms, mfu 0.02%
iter 311: loss 2.4107, time 63.69ms, mfu 0.02%
iter 312: loss 2.4517, time 59.52ms, mfu 0.02%
iter 313: loss 2.4372, time 48.13ms, mfu 0.02%
iter 314: loss 2.4837, time 60.45ms, mfu 0.02%
iter 315: loss 2.4368, time 65.12ms, mfu 0.02%
iter 316: loss 2.4451, time 59.84ms, mfu 0.02%
iter 317: loss 2.2934, time 44.78ms, mfu 0.02%
iter 318: loss 2.3787, time 43.43ms, mfu 0.02%
iter 319: loss 2.4132, time 48.81ms, mfu 0.02%
iter 320: loss 2.4062, time 73.73ms, mfu 0.02%
iter 321: loss 2.3898, time 57.94ms, mfu 0.02%
iter 322: loss 2.3933, time 49.68ms, mfu 0.02%
iter 323: loss 2.4027, time 39.04ms, mfu 0.02%
iter 324: loss 2.3942, time 35.53ms, mfu 0.03%
iter 325: loss 2.3657, time 29.27ms, mfu 0.03%
iter 326: loss 2.4684, time 40.72ms, mfu 0.03%
iter 327: loss 2.3654, time 36.22ms, mfu 0.03%
iter 328: loss 2.3823, time 51.83ms, mfu 0.03%
iter 329: loss 2.3280, time 67.21ms, mfu 0.03%
iter 330: loss 2.3390, time 37.43ms, mfu 0.03%
iter 331: loss 2.4196, time 161.99ms, mfu 0.03%
iter 332: loss 2.3537, time 1007.02ms, mfu 0.02%
iter 333: loss 2.4219, time 853.94ms, mfu 0.02%
iter 334: loss 2.3949, time 901.36ms, mfu 0.02%
iter 335: loss 2.3995, time 279.07ms, mfu 0.02%
iter 336: loss 2.4226, time 221.23ms, mfu 0.02%
iter 337: loss 2.3236, time 140.81ms, mfu 0.02%
iter 338: loss 2.3643, time 96.78ms, mfu 0.02%
iter 339: loss 2.4672, time 86.10ms, mfu 0.02%
iter 340: loss 2.3313, time 119.87ms, mfu 0.01%
iter 341: loss 2.3150, time 106.40ms, mfu 0.01%
iter 342: loss 2.3031, time 83.68ms, mfu 0.01%
iter 343: loss 2.3194, time 124.70ms, mfu 0.01%
iter 344: loss 2.4064, time 85.25ms, mfu 0.01%
iter 345: loss 2.3602, time 48.57ms, mfu 0.02%
iter 346: loss 2.3595, time 66.47ms, mfu 0.02%
iter 347: loss 2.3857, time 57.79ms, mfu 0.02%
iter 348: loss 2.3178, time 73.45ms, mfu 0.02%
iter 349: loss 2.3682, time 76.10ms, mfu 0.02%
iter 350: loss 2.3375, time 86.64ms, mfu 0.02%
iter 351: loss 2.2778, time 52.18ms, mfu 0.02%
iter 352: loss 2.3887, time 50.78ms, mfu 0.02%
iter 353: loss 2.4588, time 55.45ms, mfu 0.02%
iter 354: loss 2.3892, time 59.46ms, mfu 0.02%
iter 355: loss 2.4674, time 56.60ms, mfu 0.02%
iter 356: loss 2.2908, time 117.00ms, mfu 0.02%
iter 357: loss 2.3011, time 168.64ms, mfu 0.02%
iter 358: loss 2.3417, time 85.43ms, mfu 0.02%
iter 359: loss 2.3650, time 102.31ms, mfu 0.02%
iter 360: loss 2.4137, time 96.46ms, mfu 0.02%
iter 361: loss 2.2958, time 60.55ms, mfu 0.02%
iter 362: loss 2.3831, time 89.86ms, mfu 0.02%
iter 363: loss 2.3644, time 50.94ms, mfu 0.02%
iter 364: loss 2.3618, time 38.31ms, mfu 0.02%
iter 365: loss 2.3879, time 53.82ms, mfu 0.02%
iter 366: loss 2.4220, time 41.87ms, mfu 0.02%
iter 367: loss 2.3350, time 43.66ms, mfu 0.02%
iter 368: loss 2.3737, time 71.21ms, mfu 0.02%
iter 369: loss 2.3915, time 58.75ms, mfu 0.02%
iter 370: loss 2.4959, time 48.34ms, mfu 0.02%
iter 371: loss 2.3696, time 119.15ms, mfu 0.02%
iter 372: loss 2.3158, time 115.54ms, mfu 0.02%
iter 373: loss 2.3926, time 64.34ms, mfu 0.02%
iter 374: loss 2.3979, time 59.78ms, mfu 0.02%
iter 375: loss 2.2866, time 51.16ms, mfu 0.02%
iter 376: loss 2.3689, time 56.27ms, mfu 0.02%
iter 377: loss 2.3612, time 46.09ms, mfu 0.02%
iter 378: loss 2.3669, time 92.73ms, mfu 0.02%
iter 379: loss 2.3135, time 98.62ms, mfu 0.02%
iter 380: loss 2.3445, time 77.95ms, mfu 0.02%
iter 381: loss 2.2895, time 94.84ms, mfu 0.02%
iter 382: loss 2.4056, time 70.70ms, mfu 0.02%
iter 383: loss 2.3747, time 87.06ms, mfu 0.02%
iter 384: loss 2.2996, time 85.61ms, mfu 0.02%
iter 385: loss 2.3016, time 72.52ms, mfu 0.02%
iter 386: loss 2.3440, time 80.29ms, mfu 0.02%
iter 387: loss 2.3218, time 53.05ms, mfu 0.02%
iter 388: loss 2.2424, time 74.67ms, mfu 0.02%
iter 389: loss 2.3601, time 58.78ms, mfu 0.02%
iter 390: loss 2.3626, time 115.95ms, mfu 0.02%
iter 391: loss 2.4102, time 59.62ms, mfu 0.02%
iter 392: loss 2.2965, time 75.95ms, mfu 0.02%
iter 393: loss 2.3174, time 50.90ms, mfu 0.02%
iter 394: loss 2.4587, time 73.35ms, mfu 0.02%
iter 395: loss 2.3097, time 37.43ms, mfu 0.02%
iter 396: loss 2.3778, time 35.86ms, mfu 0.02%
iter 397: loss 2.3060, time 41.21ms, mfu 0.02%
iter 398: loss 2.2219, time 34.62ms, mfu 0.02%
iter 399: loss 2.3750, time 47.03ms, mfu 0.02%
iter 400: loss 2.3405, time 82.62ms, mfu 0.02%
iter 401: loss 2.3534, time 89.29ms, mfu 0.02%
iter 402: loss 2.3740, time 80.22ms, mfu 0.02%
iter 403: loss 2.3630, time 72.20ms, mfu 0.02%
iter 404: loss 2.3433, time 64.57ms, mfu 0.02%
iter 405: loss 2.3948, time 64.18ms, mfu 0.02%
iter 406: loss 2.3297, time 90.98ms, mfu 0.02%
iter 407: loss 2.3814, time 71.42ms, mfu 0.02%
iter 408: loss 2.2795, time 64.23ms, mfu 0.02%
iter 409: loss 2.3073, time 46.92ms, mfu 0.02%
iter 410: loss 2.2802, time 44.64ms, mfu 0.02%
iter 411: loss 2.3615, time 48.30ms, mfu 0.02%
iter 412: loss 2.3462, time 35.71ms, mfu 0.02%
iter 413: loss 2.3275, time 28.47ms, mfu 0.03%
iter 414: loss 2.3518, time 51.22ms, mfu 0.03%
iter 415: loss 2.4136, time 44.02ms, mfu 0.03%
iter 416: loss 2.3288, time 38.74ms, mfu 0.03%
iter 417: loss 2.3052, time 52.36ms, mfu 0.03%
iter 418: loss 2.2778, time 44.37ms, mfu 0.03%
iter 419: loss 2.2965, time 43.57ms, mfu 0.03%
iter 420: loss 2.3759, time 80.72ms, mfu 0.03%
iter 421: loss 2.2363, time 74.89ms, mfu 0.02%
iter 422: loss 2.2847, time 78.54ms, mfu 0.02%
iter 423: loss 2.3250, time 60.31ms, mfu 0.02%
iter 424: loss 2.2748, time 43.11ms, mfu 0.02%
iter 425: loss 2.3195, time 96.08ms, mfu 0.02%
iter 426: loss 2.4147, time 136.49ms, mfu 0.02%
iter 427: loss 2.3659, time 153.17ms, mfu 0.02%
iter 428: loss 2.3075, time 507.88ms, mfu 0.02%
iter 429: loss 2.2580, time 139.25ms, mfu 0.02%
iter 430: loss 2.4103, time 196.79ms, mfu 0.02%
iter 431: loss 2.3262, time 178.69ms, mfu 0.02%
iter 432: loss 2.3371, time 93.77ms, mfu 0.02%
iter 433: loss 2.2726, time 131.78ms, mfu 0.01%
iter 434: loss 2.2847, time 201.72ms, mfu 0.01%
iter 435: loss 2.2916, time 171.99ms, mfu 0.01%
iter 436: loss 2.3977, time 101.40ms, mfu 0.01%
iter 437: loss 2.2551, time 143.81ms, mfu 0.01%
iter 438: loss 2.2854, time 95.83ms, mfu 0.01%
iter 439: loss 2.2792, time 58.48ms, mfu 0.01%
iter 440: loss 2.3480, time 95.74ms, mfu 0.01%
iter 441: loss 2.3338, time 62.79ms, mfu 0.01%
iter 442: loss 2.3563, time 62.12ms, mfu 0.01%
iter 443: loss 2.3662, time 64.57ms, mfu 0.02%
iter 444: loss 2.3575, time 70.50ms, mfu 0.02%
iter 445: loss 2.2895, time 65.46ms, mfu 0.02%
iter 446: loss 2.2954, time 68.03ms, mfu 0.02%
iter 447: loss 2.3782, time 61.64ms, mfu 0.02%
iter 448: loss 2.3840, time 69.55ms, mfu 0.02%
iter 449: loss 2.3348, time 113.41ms, mfu 0.02%
iter 450: loss 2.3362, time 94.74ms, mfu 0.02%
iter 451: loss 2.2999, time 67.59ms, mfu 0.02%
iter 452: loss 2.3507, time 65.39ms, mfu 0.02%
iter 453: loss 2.3094, time 63.53ms, mfu 0.02%
iter 454: loss 2.3534, time 61.88ms, mfu 0.02%
iter 455: loss 2.3407, time 105.20ms, mfu 0.02%
iter 456: loss 2.3085, time 102.76ms, mfu 0.02%
iter 457: loss 2.2953, time 113.14ms, mfu 0.02%
iter 458: loss 2.2863, time 63.92ms, mfu 0.02%
iter 459: loss 2.3017, time 60.38ms, mfu 0.02%
iter 460: loss 2.3215, time 45.92ms, mfu 0.02%
iter 461: loss 2.3446, time 76.82ms, mfu 0.02%
iter 462: loss 2.3883, time 121.55ms, mfu 0.02%
iter 463: loss 2.3071, time 91.26ms, mfu 0.02%
iter 464: loss 2.2828, time 54.88ms, mfu 0.02%
iter 465: loss 2.3161, time 50.18ms, mfu 0.02%
iter 466: loss 2.2996, time 65.70ms, mfu 0.02%
iter 467: loss 2.2252, time 59.12ms, mfu 0.02%
iter 468: loss 2.2891, time 70.91ms, mfu 0.02%
iter 469: loss 2.2152, time 86.38ms, mfu 0.02%
iter 470: loss 2.2820, time 97.38ms, mfu 0.02%
iter 471: loss 2.2975, time 115.79ms, mfu 0.02%
iter 472: loss 2.2505, time 172.24ms, mfu 0.02%
iter 473: loss 2.2848, time 306.94ms, mfu 0.01%
iter 474: loss 2.2092, time 429.81ms, mfu 0.01%
iter 475: loss 2.3322, time 223.87ms, mfu 0.01%
iter 476: loss 2.2793, time 145.31ms, mfu 0.01%
iter 477: loss 2.3126, time 187.92ms, mfu 0.01%
iter 478: loss 2.3488, time 129.83ms, mfu 0.01%
iter 479: loss 2.3008, time 174.86ms, mfu 0.01%
iter 480: loss 2.2210, time 121.87ms, mfu 0.01%
iter 481: loss 2.1983, time 62.72ms, mfu 0.01%
iter 482: loss 2.3162, time 49.68ms, mfu 0.01%
iter 483: loss 2.2768, time 79.97ms, mfu 0.01%
iter 484: loss 2.2773, time 71.48ms, mfu 0.01%
iter 485: loss 2.2800, time 76.07ms, mfu 0.01%
iter 486: loss 2.2805, time 104.01ms, mfu 0.01%
iter 487: loss 2.3032, time 64.23ms, mfu 0.01%
iter 488: loss 2.3084, time 52.93ms, mfu 0.02%
iter 489: loss 2.2776, time 62.97ms, mfu 0.02%
iter 490: loss 2.3192, time 48.45ms, mfu 0.02%
iter 491: loss 2.2949, time 55.72ms, mfu 0.02%
iter 492: loss 2.3934, time 58.85ms, mfu 0.02%
iter 493: loss 2.1888, time 43.91ms, mfu 0.02%
iter 494: loss 2.3493, time 56.14ms, mfu 0.02%
iter 495: loss 2.2627, time 63.35ms, mfu 0.02%
iter 496: loss 2.2630, time 57.26ms, mfu 0.02%
iter 497: loss 2.2483, time 47.86ms, mfu 0.02%
iter 498: loss 2.3021, time 40.44ms, mfu 0.02%
iter 499: loss 2.2272, time 134.46ms, mfu 0.02%
step 500: train loss 2.2732, val loss 2.3141
saving checkpoint to out-shakespeare-char
iter 500: loss 2.3827, time 1165.63ms, mfu 0.02%
iter 501: loss 2.2468, time 84.33ms, mfu 0.02%
iter 502: loss 2.2749, time 125.05ms, mfu 0.02%
iter 503: loss 2.2869, time 66.66ms, mfu 0.02%
iter 504: loss 2.2698, time 94.21ms, mfu 0.02%
iter 505: loss 2.4110, time 111.77ms, mfu 0.02%
iter 506: loss 2.2976, time 116.90ms, mfu 0.02%
iter 507: loss 2.2620, time 95.62ms, mfu 0.02%
iter 508: loss 2.3844, time 81.47ms, mfu 0.02%
iter 509: loss 2.2737, time 104.78ms, mfu 0.02%
iter 510: loss 2.2102, time 241.68ms, mfu 0.01%
iter 511: loss 2.2610, time 717.52ms, mfu 0.01%
iter 512: loss 2.3027, time 160.42ms, mfu 0.01%
iter 513: loss 2.2255, time 106.64ms, mfu 0.01%
iter 514: loss 2.2101, time 66.16ms, mfu 0.01%
iter 515: loss 2.2562, time 105.65ms, mfu 0.01%
iter 516: loss 2.1978, time 72.58ms, mfu 0.01%
iter 517: loss 2.3188, time 108.40ms, mfu 0.01%
iter 518: loss 2.3139, time 101.16ms, mfu 0.01%
iter 519: loss 2.3065, time 84.11ms, mfu 0.01%
iter 520: loss 2.3269, time 72.10ms, mfu 0.01%
iter 521: loss 2.3028, time 95.96ms, mfu 0.01%
iter 522: loss 2.2949, time 99.00ms, mfu 0.01%
iter 523: loss 2.2880, time 59.99ms, mfu 0.01%
iter 524: loss 2.2296, time 73.22ms, mfu 0.01%
iter 525: loss 2.2265, time 74.71ms, mfu 0.01%
iter 526: loss 2.2174, time 246.23ms, mfu 0.01%
iter 527: loss 2.3135, time 143.39ms, mfu 0.01%
iter 528: loss 2.2242, time 49.50ms, mfu 0.01%
iter 529: loss 2.2512, time 67.37ms, mfu 0.02%
iter 530: loss 2.2947, time 86.15ms, mfu 0.02%
iter 531: loss 2.2396, time 41.80ms, mfu 0.02%
iter 532: loss 2.3120, time 63.82ms, mfu 0.02%
iter 533: loss 2.2841, time 101.07ms, mfu 0.02%
iter 534: loss 2.2435, time 79.54ms, mfu 0.02%
iter 535: loss 2.2502, time 64.10ms, mfu 0.02%
iter 536: loss 2.3203, time 62.54ms, mfu 0.02%
iter 537: loss 2.2272, time 76.91ms, mfu 0.02%
iter 538: loss 2.1885, time 111.46ms, mfu 0.02%
iter 539: loss 2.1655, time 97.04ms, mfu 0.02%
iter 540: loss 2.2645, time 60.12ms, mfu 0.02%
iter 541: loss 2.2189, time 121.62ms, mfu 0.02%
iter 542: loss 2.2678, time 88.76ms, mfu 0.02%
iter 543: loss 2.4016, time 71.85ms, mfu 0.02%
iter 544: loss 2.2778, time 78.00ms, mfu 0.02%
iter 545: loss 2.2472, time 61.16ms, mfu 0.02%
iter 546: loss 2.3266, time 46.64ms, mfu 0.02%
iter 547: loss 2.2237, time 86.75ms, mfu 0.02%
iter 548: loss 2.1880, time 58.32ms, mfu 0.02%
iter 549: loss 2.2061, time 94.09ms, mfu 0.02%
iter 550: loss 2.2085, time 80.75ms, mfu 0.02%
iter 551: loss 2.2311, time 50.96ms, mfu 0.02%
iter 552: loss 2.2420, time 58.17ms, mfu 0.02%
iter 553: loss 2.3390, time 52.02ms, mfu 0.02%
iter 554: loss 2.2059, time 125.83ms, mfu 0.02%
iter 555: loss 2.2399, time 110.56ms, mfu 0.02%
iter 556: loss 2.2269, time 74.69ms, mfu 0.02%
iter 557: loss 2.2081, time 150.03ms, mfu 0.02%
iter 558: loss 2.2146, time 195.24ms, mfu 0.02%
iter 559: loss 2.2311, time 1454.72ms, mfu 0.01%
iter 560: loss 2.2281, time 285.95ms, mfu 0.01%
iter 561: loss 2.2602, time 158.20ms, mfu 0.01%
iter 562: loss 2.1343, time 91.34ms, mfu 0.01%
iter 563: loss 2.2102, time 141.86ms, mfu 0.01%
iter 564: loss 2.1902, time 74.89ms, mfu 0.01%
iter 565: loss 2.1815, time 99.83ms, mfu 0.01%
iter 566: loss 2.1878, time 104.90ms, mfu 0.01%
iter 567: loss 2.2576, time 106.39ms, mfu 0.01%
iter 568: loss 2.2645, time 145.76ms, mfu 0.01%
iter 569: loss 2.2535, time 116.08ms, mfu 0.01%
iter 570: loss 2.1146, time 107.83ms, mfu 0.01%
iter 571: loss 2.1915, time 184.73ms, mfu 0.01%
iter 572: loss 2.2554, time 214.65ms, mfu 0.01%
iter 573: loss 2.2534, time 245.49ms, mfu 0.01%
iter 574: loss 2.3195, time 160.71ms, mfu 0.01%
iter 575: loss 2.2623, time 131.17ms, mfu 0.01%
iter 576: loss 2.2309, time 86.20ms, mfu 0.01%
iter 577: loss 2.2074, time 104.29ms, mfu 0.01%
iter 578: loss 2.2819, time 66.06ms, mfu 0.01%
iter 579: loss 2.2002, time 53.83ms, mfu 0.01%
iter 580: loss 2.2228, time 48.51ms, mfu 0.01%
iter 581: loss 2.3294, time 46.06ms, mfu 0.02%
iter 582: loss 2.2033, time 58.29ms, mfu 0.02%
iter 583: loss 2.2352, time 57.11ms, mfu 0.02%
iter 584: loss 2.2094, time 38.27ms, mfu 0.02%
iter 585: loss 2.2305, time 63.96ms, mfu 0.02%
iter 586: loss 2.2003, time 53.81ms, mfu 0.02%
iter 587: loss 2.2429, time 48.81ms, mfu 0.02%
iter 588: loss 2.2523, time 100.36ms, mfu 0.02%
iter 589: loss 2.1454, time 153.07ms, mfu 0.02%
iter 590: loss 2.2038, time 171.09ms, mfu 0.02%
iter 591: loss 2.1222, time 167.04ms, mfu 0.02%
iter 592: loss 2.1893, time 939.69ms, mfu 0.01%
iter 593: loss 2.2733, time 143.41ms, mfu 0.01%
iter 594: loss 2.1528, time 191.91ms, mfu 0.01%
iter 595: loss 2.1854, time 200.34ms, mfu 0.01%
iter 596: loss 2.2587, time 64.39ms, mfu 0.01%
iter 597: loss 2.2592, time 65.98ms, mfu 0.01%
iter 598: loss 2.2057, time 84.21ms, mfu 0.01%
iter 599: loss 2.1786, time 156.33ms, mfu 0.01%
iter 600: loss 2.1762, time 283.92ms, mfu 0.01%
iter 601: loss 2.2357, time 92.49ms, mfu 0.01%
iter 602: loss 2.2017, time 101.95ms, mfu 0.01%
iter 603: loss 2.1887, time 123.92ms, mfu 0.01%
iter 604: loss 2.1962, time 79.99ms, mfu 0.01%
iter 605: loss 2.2168, time 83.03ms, mfu 0.01%
iter 606: loss 2.2452, time 136.83ms, mfu 0.01%
iter 607: loss 2.2383, time 147.45ms, mfu 0.01%
iter 608: loss 2.2055, time 91.12ms, mfu 0.01%
iter 609: loss 2.1904, time 66.81ms, mfu 0.01%
iter 610: loss 2.2001, time 50.18ms, mfu 0.01%
iter 611: loss 2.1229, time 54.25ms, mfu 0.02%
iter 612: loss 2.1816, time 95.39ms, mfu 0.02%
iter 613: loss 2.1656, time 249.62ms, mfu 0.01%
iter 614: loss 2.1957, time 491.52ms, mfu 0.01%
iter 615: loss 2.2617, time 522.39ms, mfu 0.01%
iter 616: loss 2.1616, time 98.55ms, mfu 0.01%
iter 617: loss 2.2161, time 171.36ms, mfu 0.01%
iter 618: loss 2.2205, time 82.33ms, mfu 0.01%
iter 619: loss 2.2175, time 120.69ms, mfu 0.01%
iter 620: loss 2.1835, time 315.20ms, mfu 0.01%
iter 621: loss 2.1941, time 152.89ms, mfu 0.01%
iter 622: loss 2.2253, time 105.90ms, mfu 0.01%
iter 623: loss 2.2061, time 101.29ms, mfu 0.01%
iter 624: loss 2.1858, time 94.95ms, mfu 0.01%
iter 625: loss 2.2015, time 111.14ms, mfu 0.01%
iter 626: loss 2.1669, time 66.83ms, mfu 0.01%
iter 627: loss 2.1463, time 72.42ms, mfu 0.01%
iter 628: loss 2.1824, time 65.69ms, mfu 0.01%
iter 629: loss 2.2452, time 47.96ms, mfu 0.01%
iter 630: loss 2.1622, time 58.47ms, mfu 0.02%
iter 631: loss 2.1083, time 42.77ms, mfu 0.02%
iter 632: loss 2.2201, time 54.87ms, mfu 0.02%
iter 633: loss 2.1685, time 41.83ms, mfu 0.02%
iter 634: loss 2.2809, time 35.30ms, mfu 0.02%
iter 635: loss 2.2298, time 64.37ms, mfu 0.02%
iter 636: loss 2.2056, time 39.73ms, mfu 0.02%
iter 637: loss 2.1337, time 37.59ms, mfu 0.02%
iter 638: loss 2.1657, time 54.78ms, mfu 0.02%
iter 639: loss 2.2416, time 59.45ms, mfu 0.02%
iter 640: loss 2.1233, time 82.79ms, mfu 0.02%
iter 641: loss 2.2060, time 93.38ms, mfu 0.02%
iter 642: loss 2.2535, time 64.39ms, mfu 0.02%
iter 643: loss 2.1925, time 91.90ms, mfu 0.02%
iter 644: loss 2.2023, time 113.06ms, mfu 0.02%
iter 645: loss 2.1416, time 112.81ms, mfu 0.02%
iter 646: loss 2.2024, time 91.49ms, mfu 0.02%
iter 647: loss 2.1978, time 56.34ms, mfu 0.02%
iter 648: loss 2.1226, time 58.53ms, mfu 0.02%
iter 649: loss 2.1907, time 64.58ms, mfu 0.02%
iter 650: loss 2.1471, time 67.35ms, mfu 0.02%
iter 651: loss 2.1497, time 122.85ms, mfu 0.02%
iter 652: loss 2.2072, time 103.95ms, mfu 0.02%
iter 653: loss 2.2927, time 254.43ms, mfu 0.02%
iter 654: loss 2.1618, time 199.00ms, mfu 0.02%
iter 655: loss 2.1870, time 179.07ms, mfu 0.01%
iter 656: loss 2.2226, time 241.77ms, mfu 0.01%
iter 657: loss 2.2553, time 215.25ms, mfu 0.01%
iter 658: loss 2.3203, time 229.85ms, mfu 0.01%
iter 659: loss 2.0763, time 121.46ms, mfu 0.01%
iter 660: loss 2.2185, time 119.42ms, mfu 0.01%
iter 661: loss 2.1899, time 61.89ms, mfu 0.01%
iter 662: loss 2.1839, time 52.06ms, mfu 0.01%
iter 663: loss 2.1789, time 62.41ms, mfu 0.01%
iter 664: loss 2.1137, time 52.54ms, mfu 0.02%
iter 665: loss 2.1452, time 68.38ms, mfu 0.02%
iter 666: loss 2.1240, time 45.75ms, mfu 0.02%
iter 667: loss 2.2286, time 57.71ms, mfu 0.02%
iter 668: loss 2.2215, time 69.97ms, mfu 0.02%
iter 669: loss 2.1907, time 93.76ms, mfu 0.02%
iter 670: loss 2.1319, time 85.03ms, mfu 0.02%
iter 671: loss 2.1905, time 55.62ms, mfu 0.02%
iter 672: loss 2.2237, time 228.42ms, mfu 0.02%
iter 673: loss 2.1459, time 115.28ms, mfu 0.02%
iter 674: loss 2.1634, time 76.88ms, mfu 0.02%
iter 675: loss 2.2517, time 75.64ms, mfu 0.02%
iter 676: loss 2.2451, time 72.11ms, mfu 0.02%
iter 677: loss 2.2100, time 43.60ms, mfu 0.02%
iter 678: loss 2.1692, time 94.69ms, mfu 0.02%
iter 679: loss 2.1280, time 77.59ms, mfu 0.02%
iter 680: loss 2.1610, time 99.52ms, mfu 0.02%
iter 681: loss 2.2499, time 108.37ms, mfu 0.02%
iter 682: loss 2.2104, time 95.60ms, mfu 0.02%
iter 683: loss 2.1459, time 89.64ms, mfu 0.02%
iter 684: loss 2.1459, time 85.02ms, mfu 0.02%
iter 685: loss 2.1823, time 55.31ms, mfu 0.02%
iter 686: loss 2.1284, time 74.69ms, mfu 0.02%
iter 687: loss 2.0909, time 95.48ms, mfu 0.02%
iter 688: loss 2.2150, time 94.58ms, mfu 0.02%
iter 689: loss 2.1008, time 72.43ms, mfu 0.02%
iter 690: loss 2.0918, time 96.17ms, mfu 0.02%
iter 691: loss 2.0587, time 121.04ms, mfu 0.02%
iter 692: loss 2.1489, time 118.04ms, mfu 0.01%
iter 693: loss 2.1889, time 119.62ms, mfu 0.01%
iter 694: loss 2.2110, time 86.98ms, mfu 0.01%
iter 695: loss 2.0026, time 83.37ms, mfu 0.01%
iter 696: loss 2.1394, time 131.08ms, mfu 0.01%
iter 697: loss 2.2696, time 78.47ms, mfu 0.01%
iter 698: loss 2.1552, time 118.14ms, mfu 0.01%
iter 699: loss 2.1777, time 79.38ms, mfu 0.01%
iter 700: loss 2.0947, time 306.39ms, mfu 0.01%
iter 701: loss 2.0826, time 318.54ms, mfu 0.01%
iter 702: loss 2.2262, time 198.63ms, mfu 0.01%
iter 703: loss 2.1844, time 145.68ms, mfu 0.01%
iter 704: loss 2.0627, time 151.78ms, mfu 0.01%
iter 705: loss 2.1286, time 157.00ms, mfu 0.01%
iter 706: loss 2.2228, time 111.09ms, mfu 0.01%
iter 707: loss 2.0659, time 127.95ms, mfu 0.01%
iter 708: loss 2.0816, time 109.95ms, mfu 0.01%
iter 709: loss 2.1770, time 83.78ms, mfu 0.01%
iter 710: loss 2.1849, time 77.06ms, mfu 0.01%
iter 711: loss 2.1218, time 61.40ms, mfu 0.01%
iter 712: loss 2.2316, time 58.26ms, mfu 0.01%
iter 713: loss 2.0327, time 65.96ms, mfu 0.01%
iter 714: loss 2.0841, time 78.28ms, mfu 0.01%
iter 715: loss 2.0609, time 80.13ms, mfu 0.01%
iter 716: loss 2.1239, time 95.23ms, mfu 0.01%
iter 717: loss 2.1714, time 97.88ms, mfu 0.01%
iter 718: loss 2.1281, time 233.73ms, mfu 0.01%
iter 719: loss 2.1241, time 101.61ms, mfu 0.01%
iter 720: loss 2.1115, time 62.37ms, mfu 0.01%
iter 721: loss 2.2540, time 75.21ms, mfu 0.01%
iter 722: loss 2.0898, time 56.74ms, mfu 0.02%
iter 723: loss 2.0718, time 57.33ms, mfu 0.02%
iter 724: loss 2.1135, time 55.22ms, mfu 0.02%
iter 725: loss 2.2130, time 75.36ms, mfu 0.02%
iter 726: loss 2.1488, time 128.73ms, mfu 0.02%
iter 727: loss 2.1094, time 109.77ms, mfu 0.02%
iter 728: loss 2.1599, time 63.04ms, mfu 0.02%
iter 729: loss 2.1785, time 50.81ms, mfu 0.02%
iter 730: loss 2.1955, time 55.08ms, mfu 0.02%
iter 731: loss 2.1662, time 69.28ms, mfu 0.02%
iter 732: loss 2.1308, time 42.92ms, mfu 0.02%
iter 733: loss 2.1017, time 51.57ms, mfu 0.02%
iter 734: loss 2.0702, time 47.33ms, mfu 0.02%
iter 735: loss 2.1047, time 49.06ms, mfu 0.02%
iter 736: loss 2.1177, time 47.23ms, mfu 0.02%
iter 737: loss 2.2741, time 35.93ms, mfu 0.02%
iter 738: loss 2.0233, time 40.03ms, mfu 0.02%
iter 739: loss 2.1258, time 39.80ms, mfu 0.02%
iter 740: loss 2.1313, time 38.90ms, mfu 0.03%
iter 741: loss 2.0251, time 53.19ms, mfu 0.03%
iter 742: loss 2.1406, time 60.70ms, mfu 0.02%
iter 743: loss 2.1731, time 106.82ms, mfu 0.02%
iter 744: loss 2.1083, time 130.25ms, mfu 0.02%
iter 745: loss 2.0706, time 66.86ms, mfu 0.02%
iter 746: loss 2.0784, time 166.50ms, mfu 0.02%
iter 747: loss 2.0538, time 126.91ms, mfu 0.02%
iter 748: loss 2.0627, time 67.88ms, mfu 0.02%
iter 749: loss 2.0851, time 76.01ms, mfu 0.02%
step 750: train loss 2.1338, val loss 2.1905
saving checkpoint to out-shakespeare-char
iter 750: loss 2.0768, time 1133.31ms, mfu 0.02%
iter 751: loss 2.1407, time 67.40ms, mfu 0.02%
iter 752: loss 2.1244, time 101.90ms, mfu 0.02%
iter 753: loss 2.0533, time 374.63ms, mfu 0.02%
iter 754: loss 2.1386, time 92.69ms, mfu 0.02%
iter 755: loss 2.0479, time 65.14ms, mfu 0.02%
iter 756: loss 2.0506, time 46.39ms, mfu 0.02%
iter 757: loss 2.1101, time 54.15ms, mfu 0.02%
iter 758: loss 2.1412, time 86.46ms, mfu 0.02%
iter 759: loss 2.1293, time 70.67ms, mfu 0.02%
iter 760: loss 2.1775, time 57.76ms, mfu 0.02%
iter 761: loss 2.1686, time 87.66ms, mfu 0.02%
iter 762: loss 2.1632, time 88.47ms, mfu 0.02%
iter 763: loss 2.1387, time 136.31ms, mfu 0.02%
iter 764: loss 2.1546, time 117.93ms, mfu 0.02%
iter 765: loss 2.0865, time 204.28ms, mfu 0.01%
iter 766: loss 2.1429, time 116.54ms, mfu 0.01%
iter 767: loss 2.1232, time 84.14ms, mfu 0.01%
iter 768: loss 2.1197, time 87.21ms, mfu 0.01%
iter 769: loss 2.0845, time 42.91ms, mfu 0.02%
iter 770: loss 2.1071, time 54.78ms, mfu 0.02%
iter 771: loss 2.1252, time 47.83ms, mfu 0.02%
iter 772: loss 2.1457, time 46.14ms, mfu 0.02%
iter 773: loss 2.1527, time 98.69ms, mfu 0.02%
iter 774: loss 2.0532, time 147.67ms, mfu 0.02%
iter 775: loss 2.0334, time 162.99ms, mfu 0.02%
iter 776: loss 2.1300, time 219.34ms, mfu 0.02%
iter 777: loss 2.1024, time 194.84ms, mfu 0.01%
iter 778: loss 2.0927, time 486.61ms, mfu 0.01%
iter 779: loss 2.0962, time 499.01ms, mfu 0.01%
iter 780: loss 2.0800, time 157.53ms, mfu 0.01%
iter 781: loss 2.0187, time 308.91ms, mfu 0.01%
iter 782: loss 2.1151, time 290.08ms, mfu 0.01%
iter 783: loss 2.2014, time 67.37ms, mfu 0.01%
iter 784: loss 2.2639, time 78.39ms, mfu 0.01%
iter 785: loss 2.0340, time 51.65ms, mfu 0.01%
iter 786: loss 2.0403, time 57.96ms, mfu 0.01%
iter 787: loss 2.0703, time 79.03ms, mfu 0.01%
iter 788: loss 2.2301, time 78.26ms, mfu 0.01%
iter 789: loss 2.1560, time 101.65ms, mfu 0.01%
iter 790: loss 2.0264, time 72.27ms, mfu 0.01%
iter 791: loss 2.0941, time 80.95ms, mfu 0.01%
iter 792: loss 2.0005, time 89.03ms, mfu 0.01%
iter 793: loss 2.1123, time 78.45ms, mfu 0.01%
iter 794: loss 2.1383, time 101.07ms, mfu 0.01%
iter 795: loss 2.2083, time 82.38ms, mfu 0.01%
iter 796: loss 2.1705, time 78.67ms, mfu 0.01%
iter 797: loss 2.1470, time 87.51ms, mfu 0.01%
iter 798: loss 2.1218, time 55.35ms, mfu 0.02%
iter 799: loss 2.0639, time 63.05ms, mfu 0.02%
iter 800: loss 2.2092, time 50.54ms, mfu 0.02%
iter 801: loss 2.1228, time 51.65ms, mfu 0.02%
iter 802: loss 2.1245, time 90.73ms, mfu 0.02%
iter 803: loss 2.1444, time 117.76ms, mfu 0.02%
iter 804: loss 2.1201, time 119.06ms, mfu 0.02%
iter 805: loss 2.0980, time 293.86ms, mfu 0.01%
iter 806: loss 2.1103, time 281.57ms, mfu 0.01%
iter 807: loss 1.9970, time 154.29ms, mfu 0.01%
iter 808: loss 2.1820, time 162.72ms, mfu 0.01%
iter 809: loss 2.1460, time 149.18ms, mfu 0.01%
iter 810: loss 2.0301, time 471.12ms, mfu 0.01%
iter 811: loss 2.1747, time 590.30ms, mfu 0.01%
iter 812: loss 2.0890, time 210.87ms, mfu 0.01%
iter 813: loss 2.0966, time 155.80ms, mfu 0.01%
iter 814: loss 2.1267, time 126.67ms, mfu 0.01%
iter 815: loss 2.2304, time 167.62ms, mfu 0.01%
iter 816: loss 2.0944, time 274.69ms, mfu 0.01%
iter 817: loss 2.0696, time 161.55ms, mfu 0.01%
iter 818: loss 2.0443, time 114.51ms, mfu 0.01%
iter 819: loss 2.1775, time 119.88ms, mfu 0.01%
iter 820: loss 2.0808, time 70.87ms, mfu 0.01%
iter 821: loss 2.0726, time 61.37ms, mfu 0.01%
iter 822: loss 2.1358, time 52.51ms, mfu 0.01%
iter 823: loss 2.0497, time 64.70ms, mfu 0.01%
iter 824: loss 2.0255, time 51.26ms, mfu 0.01%
iter 825: loss 2.1156, time 57.60ms, mfu 0.02%
iter 826: loss 2.1116, time 103.50ms, mfu 0.01%
iter 827: loss 2.1186, time 146.03ms, mfu 0.01%
iter 828: loss 2.0776, time 86.48ms, mfu 0.01%
iter 829: loss 1.9653, time 60.12ms, mfu 0.02%
iter 830: loss 2.0330, time 146.33ms, mfu 0.01%
iter 831: loss 2.1503, time 270.28ms, mfu 0.01%
iter 832: loss 2.0106, time 81.22ms, mfu 0.01%
iter 833: loss 2.0833, time 78.26ms, mfu 0.01%
iter 834: loss 2.1326, time 70.51ms, mfu 0.01%
iter 835: loss 2.1199, time 69.83ms, mfu 0.01%
iter 836: loss 2.0372, time 97.27ms, mfu 0.01%
iter 837: loss 2.2104, time 152.98ms, mfu 0.01%
iter 838: loss 2.1157, time 54.92ms, mfu 0.01%
iter 839: loss 2.1274, time 51.33ms, mfu 0.02%
iter 840: loss 2.0744, time 45.62ms, mfu 0.02%
iter 841: loss 2.0000, time 48.41ms, mfu 0.02%
iter 842: loss 2.0769, time 54.60ms, mfu 0.02%
iter 843: loss 2.0576, time 82.74ms, mfu 0.02%
iter 844: loss 2.1378, time 52.96ms, mfu 0.02%
iter 845: loss 2.0132, time 54.44ms, mfu 0.02%
iter 846: loss 2.1043, time 68.77ms, mfu 0.02%
iter 847: loss 1.9704, time 72.82ms, mfu 0.02%
iter 848: loss 1.9988, time 386.03ms, mfu 0.02%
iter 849: loss 2.0418, time 433.74ms, mfu 0.02%
iter 850: loss 2.0917, time 176.64ms, mfu 0.02%
iter 851: loss 2.1259, time 140.96ms, mfu 0.01%
iter 852: loss 2.0850, time 296.85ms, mfu 0.01%
iter 853: loss 2.1108, time 120.90ms, mfu 0.01%
iter 854: loss 2.0620, time 91.94ms, mfu 0.01%
iter 855: loss 2.0700, time 78.85ms, mfu 0.01%
iter 856: loss 1.9849, time 92.91ms, mfu 0.01%
iter 857: loss 2.1726, time 76.65ms, mfu 0.01%
iter 858: loss 2.0617, time 59.24ms, mfu 0.01%
iter 859: loss 2.1456, time 118.46ms, mfu 0.01%
iter 860: loss 2.1284, time 159.32ms, mfu 0.01%
iter 861: loss 2.0030, time 138.55ms, mfu 0.01%
iter 862: loss 2.0335, time 167.64ms, mfu 0.01%
iter 863: loss 2.0240, time 91.11ms, mfu 0.01%
iter 864: loss 1.8698, time 92.16ms, mfu 0.01%
iter 865: loss 2.0460, time 83.74ms, mfu 0.01%
iter 866: loss 2.0577, time 64.56ms, mfu 0.01%
iter 867: loss 2.0163, time 62.04ms, mfu 0.01%
iter 868: loss 2.0983, time 103.20ms, mfu 0.01%
iter 869: loss 2.0579, time 113.81ms, mfu 0.01%
iter 870: loss 2.0902, time 105.42ms, mfu 0.01%
iter 871: loss 2.0539, time 161.76ms, mfu 0.01%
iter 872: loss 2.0660, time 95.13ms, mfu 0.01%
iter 873: loss 2.0734, time 82.67ms, mfu 0.01%
iter 874: loss 2.0514, time 78.49ms, mfu 0.01%
iter 875: loss 2.1123, time 235.45ms, mfu 0.01%
iter 876: loss 2.0686, time 156.07ms, mfu 0.01%
iter 877: loss 2.0769, time 78.08ms, mfu 0.01%
iter 878: loss 2.0774, time 83.43ms, mfu 0.01%
iter 879: loss 1.9879, time 301.71ms, mfu 0.01%
iter 880: loss 2.0552, time 218.36ms, mfu 0.01%
iter 881: loss 2.0070, time 589.57ms, mfu 0.01%
iter 882: loss 1.9897, time 295.97ms, mfu 0.01%
iter 883: loss 2.0791, time 301.03ms, mfu 0.01%
iter 884: loss 2.0410, time 192.61ms, mfu 0.01%
iter 885: loss 2.0493, time 224.33ms, mfu 0.01%
iter 886: loss 1.9413, time 245.77ms, mfu 0.01%
iter 887: loss 1.9713, time 218.85ms, mfu 0.01%
iter 888: loss 2.0845, time 169.35ms, mfu 0.01%
iter 889: loss 2.0774, time 213.49ms, mfu 0.01%
iter 890: loss 1.9706, time 116.99ms, mfu 0.01%
iter 891: loss 2.0223, time 109.78ms, mfu 0.01%
iter 892: loss 2.0640, time 62.03ms, mfu 0.01%
iter 893: loss 2.0120, time 50.94ms, mfu 0.01%
iter 894: loss 2.0396, time 60.71ms, mfu 0.01%
iter 895: loss 2.0066, time 54.00ms, mfu 0.01%
iter 896: loss 2.1424, time 53.43ms, mfu 0.01%
iter 897: loss 1.9973, time 63.59ms, mfu 0.01%
iter 898: loss 2.0522, time 58.82ms, mfu 0.02%
iter 899: loss 2.0506, time 44.73ms, mfu 0.02%
iter 900: loss 2.0011, time 51.20ms, mfu 0.02%
iter 901: loss 2.0311, time 68.76ms, mfu 0.02%
iter 902: loss 2.0733, time 54.42ms, mfu 0.02%
iter 903: loss 2.0824, time 79.69ms, mfu 0.02%
iter 904: loss 2.1021, time 58.80ms, mfu 0.02%
iter 905: loss 2.0285, time 70.63ms, mfu 0.02%
iter 906: loss 2.1380, time 48.43ms, mfu 0.02%
iter 907: loss 2.0708, time 42.16ms, mfu 0.02%
iter 908: loss 2.0270, time 69.25ms, mfu 0.02%
iter 909: loss 1.9628, time 72.21ms, mfu 0.02%
iter 910: loss 1.9365, time 51.81ms, mfu 0.02%
iter 911: loss 2.0287, time 60.19ms, mfu 0.02%
iter 912: loss 2.1096, time 45.04ms, mfu 0.02%
iter 913: loss 2.0701, time 48.24ms, mfu 0.02%
iter 914: loss 2.0542, time 67.15ms, mfu 0.02%
iter 915: loss 2.0517, time 64.76ms, mfu 0.02%
iter 916: loss 2.0870, time 66.76ms, mfu 0.02%
iter 917: loss 1.9541, time 64.40ms, mfu 0.02%
iter 918: loss 2.0061, time 50.62ms, mfu 0.02%
iter 919: loss 2.0926, time 48.98ms, mfu 0.02%
iter 920: loss 2.0709, time 75.16ms, mfu 0.02%
iter 921: loss 1.9773, time 53.87ms, mfu 0.02%
iter 922: loss 2.1213, time 56.84ms, mfu 0.02%
iter 923: loss 2.0736, time 259.73ms, mfu 0.02%
iter 924: loss 1.9797, time 92.88ms, mfu 0.02%
iter 925: loss 1.9758, time 78.16ms, mfu 0.02%
iter 926: loss 2.0349, time 89.45ms, mfu 0.02%
iter 927: loss 1.9805, time 86.41ms, mfu 0.02%
iter 928: loss 2.0132, time 50.08ms, mfu 0.02%
iter 929: loss 1.9769, time 49.87ms, mfu 0.02%
iter 930: loss 2.0989, time 55.09ms, mfu 0.02%
iter 931: loss 2.0028, time 100.43ms, mfu 0.02%
iter 932: loss 2.0502, time 283.43ms, mfu 0.02%
iter 933: loss 2.0049, time 479.48ms, mfu 0.02%
iter 934: loss 1.9724, time 166.74ms, mfu 0.02%
iter 935: loss 2.1588, time 553.10ms, mfu 0.01%
iter 936: loss 2.0550, time 482.37ms, mfu 0.01%
iter 937: loss 2.0525, time 355.33ms, mfu 0.01%
iter 938: loss 2.0305, time 261.99ms, mfu 0.01%
iter 939: loss 2.0991, time 164.20ms, mfu 0.01%
iter 940: loss 1.9304, time 146.20ms, mfu 0.01%
iter 941: loss 2.1198, time 107.27ms, mfu 0.01%
iter 942: loss 2.0252, time 107.15ms, mfu 0.01%
iter 943: loss 2.0708, time 90.58ms, mfu 0.01%
iter 944: loss 2.1878, time 139.53ms, mfu 0.01%
iter 945: loss 2.0171, time 78.65ms, mfu 0.01%
iter 946: loss 2.0426, time 116.61ms, mfu 0.01%
iter 947: loss 2.1607, time 77.82ms, mfu 0.01%
iter 948: loss 2.0450, time 59.64ms, mfu 0.01%
iter 949: loss 1.9960, time 69.44ms, mfu 0.01%
iter 950: loss 2.0163, time 45.56ms, mfu 0.01%
iter 951: loss 2.0025, time 42.85ms, mfu 0.02%
iter 952: loss 1.9233, time 77.24ms, mfu 0.02%
iter 953: loss 2.0273, time 68.45ms, mfu 0.02%
iter 954: loss 1.9408, time 95.87ms, mfu 0.02%
iter 955: loss 1.9250, time 79.58ms, mfu 0.02%
iter 956: loss 1.9735, time 195.31ms, mfu 0.02%
iter 957: loss 2.0590, time 94.52ms, mfu 0.02%
iter 958: loss 1.9693, time 75.71ms, mfu 0.02%
iter 959: loss 2.0408, time 94.69ms, mfu 0.02%
iter 960: loss 2.0722, time 57.10ms, mfu 0.02%
iter 961: loss 2.0412, time 113.42ms, mfu 0.02%
iter 962: loss 1.8536, time 96.62ms, mfu 0.02%
iter 963: loss 2.0340, time 78.34ms, mfu 0.02%
iter 964: loss 1.9469, time 90.44ms, mfu 0.02%
iter 965: loss 2.0986, time 83.83ms, mfu 0.02%
iter 966: loss 2.0314, time 63.62ms, mfu 0.02%
iter 967: loss 2.0290, time 56.68ms, mfu 0.02%
iter 968: loss 1.9671, time 49.85ms, mfu 0.02%
iter 969: loss 2.0317, time 73.51ms, mfu 0.02%
iter 970: loss 1.9988, time 57.45ms, mfu 0.02%
iter 971: loss 2.0281, time 70.20ms, mfu 0.02%
iter 972: loss 2.0254, time 60.19ms, mfu 0.02%
iter 973: loss 2.0472, time 88.59ms, mfu 0.02%
iter 974: loss 2.0509, time 131.18ms, mfu 0.02%
iter 975: loss 2.0205, time 474.88ms, mfu 0.02%
iter 976: loss 1.9363, time 284.68ms, mfu 0.01%
iter 977: loss 1.9784, time 137.11ms, mfu 0.01%
iter 978: loss 1.9620, time 154.89ms, mfu 0.01%
iter 979: loss 2.0388, time 203.66ms, mfu 0.01%
iter 980: loss 2.0707, time 116.93ms, mfu 0.01%
iter 981: loss 1.9428, time 149.62ms, mfu 0.01%
iter 982: loss 1.9679, time 115.61ms, mfu 0.01%
iter 983: loss 1.9931, time 115.29ms, mfu 0.01%
iter 984: loss 2.0907, time 122.14ms, mfu 0.01%
iter 985: loss 1.9108, time 171.05ms, mfu 0.01%
iter 986: loss 1.8807, time 172.17ms, mfu 0.01%
iter 987: loss 2.1196, time 154.42ms, mfu 0.01%
iter 988: loss 2.0061, time 123.46ms, mfu 0.01%
iter 989: loss 2.1192, time 152.79ms, mfu 0.01%
iter 990: loss 2.0501, time 46.67ms, mfu 0.01%
iter 991: loss 2.0294, time 74.29ms, mfu 0.01%
iter 992: loss 1.8942, time 93.48ms, mfu 0.01%
iter 993: loss 2.0586, time 68.85ms, mfu 0.01%
iter 994: loss 2.0846, time 122.24ms, mfu 0.01%
iter 995: loss 2.0892, time 81.80ms, mfu 0.01%
iter 996: loss 1.9608, time 157.18ms, mfu 0.01%
iter 997: loss 1.9493, time 290.79ms, mfu 0.01%
iter 998: loss 1.8290, time 144.28ms, mfu 0.01%
iter 999: loss 1.9259, time 97.33ms, mfu 0.01%
step 1000: train loss 1.9714, val loss 2.0528
saving checkpoint to out-shakespeare-char
iter 1000: loss 2.0455, time 1222.75ms, mfu 0.01%
iter 1001: loss 1.9187, time 248.94ms, mfu 0.01%
iter 1002: loss 2.0082, time 172.11ms, mfu 0.01%
iter 1003: loss 2.0436, time 215.17ms, mfu 0.01%
iter 1004: loss 1.9564, time 56.46ms, mfu 0.01%
iter 1005: loss 2.0181, time 99.15ms, mfu 0.01%
iter 1006: loss 1.9583, time 105.69ms, mfu 0.01%
iter 1007: loss 2.0487, time 152.62ms, mfu 0.01%
iter 1008: loss 1.9878, time 73.33ms, mfu 0.01%
iter 1009: loss 1.9712, time 45.37ms, mfu 0.01%
iter 1010: loss 2.0443, time 100.89ms, mfu 0.01%
iter 1011: loss 2.0011, time 89.09ms, mfu 0.01%
iter 1012: loss 1.9721, time 64.39ms, mfu 0.01%
iter 1013: loss 1.8608, time 43.02ms, mfu 0.02%
iter 1014: loss 1.9983, time 44.90ms, mfu 0.02%
iter 1015: loss 2.0427, time 42.30ms, mfu 0.02%
iter 1016: loss 2.1544, time 76.27ms, mfu 0.02%
iter 1017: loss 2.0251, time 62.97ms, mfu 0.02%
iter 1018: loss 2.0941, time 56.95ms, mfu 0.02%
iter 1019: loss 2.0758, time 47.00ms, mfu 0.02%
iter 1020: loss 1.9418, time 59.10ms, mfu 0.02%
iter 1021: loss 1.9768, time 79.36ms, mfu 0.02%
iter 1022: loss 2.0440, time 70.62ms, mfu 0.02%
iter 1023: loss 2.0341, time 133.02ms, mfu 0.02%
iter 1024: loss 1.9736, time 230.51ms, mfu 0.02%
iter 1025: loss 1.9829, time 646.75ms, mfu 0.02%
iter 1026: loss 1.9681, time 1065.06ms, mfu 0.01%
iter 1027: loss 1.9797, time 437.26ms, mfu 0.01%
iter 1028: loss 2.1521, time 97.01ms, mfu 0.01%
iter 1029: loss 2.0399, time 153.97ms, mfu 0.01%
iter 1030: loss 2.0274, time 86.41ms, mfu 0.01%
iter 1031: loss 1.9911, time 112.84ms, mfu 0.01%
iter 1032: loss 2.1031, time 162.41ms, mfu 0.01%
iter 1033: loss 2.0002, time 281.28ms, mfu 0.01%
iter 1034: loss 1.9311, time 179.39ms, mfu 0.01%
iter 1035: loss 2.0402, time 182.90ms, mfu 0.01%
iter 1036: loss 1.9620, time 116.46ms, mfu 0.01%
iter 1037: loss 1.9719, time 90.40ms, mfu 0.01%
iter 1038: loss 1.9493, time 80.37ms, mfu 0.01%
iter 1039: loss 2.0411, time 84.20ms, mfu 0.01%
iter 1040: loss 1.9650, time 84.40ms, mfu 0.01%
iter 1041: loss 2.0880, time 170.11ms, mfu 0.01%
iter 1042: loss 1.9858, time 161.35ms, mfu 0.01%
iter 1043: loss 2.0099, time 158.16ms, mfu 0.01%
iter 1044: loss 2.0070, time 69.73ms, mfu 0.01%
iter 1045: loss 1.9664, time 63.00ms, mfu 0.01%
iter 1046: loss 1.9515, time 60.41ms, mfu 0.01%
iter 1047: loss 2.0003, time 64.67ms, mfu 0.01%
iter 1048: loss 1.9025, time 91.62ms, mfu 0.01%
iter 1049: loss 1.9591, time 137.70ms, mfu 0.01%
iter 1050: loss 1.9098, time 169.16ms, mfu 0.01%
iter 1051: loss 1.9447, time 207.28ms, mfu 0.01%
iter 1052: loss 2.0019, time 72.11ms, mfu 0.01%
iter 1053: loss 2.0268, time 42.19ms, mfu 0.01%
iter 1054: loss 2.0150, time 74.32ms, mfu 0.01%
iter 1055: loss 2.0053, time 60.58ms, mfu 0.02%
iter 1056: loss 1.9245, time 55.99ms, mfu 0.02%
iter 1057: loss 1.9400, time 77.30ms, mfu 0.02%
iter 1058: loss 2.0402, time 47.20ms, mfu 0.02%
iter 1059: loss 1.9493, time 54.25ms, mfu 0.02%
iter 1060: loss 1.9377, time 72.45ms, mfu 0.02%
iter 1061: loss 1.8814, time 80.11ms, mfu 0.02%
iter 1062: loss 1.9186, time 181.61ms, mfu 0.02%
iter 1063: loss 2.0572, time 971.86ms, mfu 0.02%
iter 1064: loss 1.9428, time 240.60ms, mfu 0.01%
iter 1065: loss 1.9515, time 128.91ms, mfu 0.01%
iter 1066: loss 2.0536, time 164.73ms, mfu 0.01%
iter 1067: loss 2.0140, time 110.90ms, mfu 0.01%
iter 1068: loss 2.0928, time 193.76ms, mfu 0.01%
iter 1069: loss 1.9994, time 96.71ms, mfu 0.01%
iter 1070: loss 1.9572, time 143.14ms, mfu 0.01%
iter 1071: loss 1.9742, time 78.43ms, mfu 0.01%
iter 1072: loss 2.0662, time 40.86ms, mfu 0.01%
iter 1073: loss 1.9530, time 66.62ms, mfu 0.01%
iter 1074: loss 2.0061, time 43.64ms, mfu 0.02%
iter 1075: loss 2.0648, time 57.06ms, mfu 0.02%
iter 1076: loss 1.9733, time 68.71ms, mfu 0.02%
iter 1077: loss 1.9448, time 123.05ms, mfu 0.02%
iter 1078: loss 1.9525, time 81.19ms, mfu 0.02%
iter 1079: loss 1.8720, time 85.55ms, mfu 0.02%
iter 1080: loss 2.1023, time 131.15ms, mfu 0.02%
iter 1081: loss 1.9793, time 131.51ms, mfu 0.01%
iter 1082: loss 1.9812, time 88.95ms, mfu 0.01%
iter 1083: loss 2.0209, time 91.89ms, mfu 0.01%
iter 1084: loss 2.0688, time 105.40ms, mfu 0.01%
iter 1085: loss 1.9859, time 92.86ms, mfu 0.01%
iter 1086: loss 1.9598, time 64.94ms, mfu 0.01%
iter 1087: loss 1.9040, time 80.07ms, mfu 0.02%
iter 1088: loss 1.8467, time 100.80ms, mfu 0.01%
iter 1089: loss 1.9743, time 65.14ms, mfu 0.02%
iter 1090: loss 1.9512, time 63.64ms, mfu 0.02%
iter 1091: loss 1.9888, time 118.34ms, mfu 0.02%
iter 1092: loss 1.9321, time 176.02ms, mfu 0.01%
iter 1093: loss 2.0330, time 97.61ms, mfu 0.01%
iter 1094: loss 2.0521, time 129.88ms, mfu 0.01%
iter 1095: loss 2.0652, time 63.31ms, mfu 0.01%
iter 1096: loss 2.0213, time 79.82ms, mfu 0.01%
iter 1097: loss 2.0423, time 76.96ms, mfu 0.01%
iter 1098: loss 1.9557, time 87.91ms, mfu 0.01%
iter 1099: loss 1.9890, time 79.99ms, mfu 0.01%
iter 1100: loss 1.7907, time 93.72ms, mfu 0.01%
iter 1101: loss 1.9019, time 127.92ms, mfu 0.01%
iter 1102: loss 1.9016, time 267.14ms, mfu 0.01%
iter 1103: loss 1.9404, time 102.02ms, mfu 0.01%
iter 1104: loss 1.9233, time 60.43ms, mfu 0.01%
iter 1105: loss 1.9644, time 69.81ms, mfu 0.01%
iter 1106: loss 2.0463, time 78.11ms, mfu 0.01%
iter 1107: loss 1.9365, time 58.60ms, mfu 0.02%
iter 1108: loss 1.9146, time 118.32ms, mfu 0.01%
iter 1109: loss 1.9921, time 100.83ms, mfu 0.01%
iter 1110: loss 1.9410, time 155.22ms, mfu 0.01%
iter 1111: loss 1.9718, time 236.14ms, mfu 0.01%
iter 1112: loss 1.8669, time 113.77ms, mfu 0.01%
iter 1113: loss 1.9348, time 131.23ms, mfu 0.01%
iter 1114: loss 1.8593, time 136.23ms, mfu 0.01%
iter 1115: loss 1.9424, time 93.35ms, mfu 0.01%
iter 1116: loss 1.8555, time 93.27ms, mfu 0.01%
iter 1117: loss 2.0105, time 76.87ms, mfu 0.01%
iter 1118: loss 2.0644, time 88.88ms, mfu 0.01%
iter 1119: loss 1.9743, time 106.05ms, mfu 0.01%
iter 1120: loss 1.9305, time 190.09ms, mfu 0.01%
iter 1121: loss 1.9816, time 110.48ms, mfu 0.01%
iter 1122: loss 1.8883, time 70.91ms, mfu 0.01%
iter 1123: loss 1.9025, time 76.21ms, mfu 0.01%
iter 1124: loss 1.9972, time 55.63ms, mfu 0.01%
iter 1125: loss 1.9137, time 56.89ms, mfu 0.02%
iter 1126: loss 1.9450, time 91.21ms, mfu 0.01%
iter 1127: loss 1.8206, time 71.76ms, mfu 0.02%
iter 1128: loss 1.9851, time 76.68ms, mfu 0.02%
iter 1129: loss 1.9800, time 76.89ms, mfu 0.02%
iter 1130: loss 1.8721, time 107.47ms, mfu 0.02%
iter 1131: loss 1.8721, time 92.20ms, mfu 0.01%
iter 1132: loss 2.0754, time 76.06ms, mfu 0.02%
iter 1133: loss 1.9428, time 65.26ms, mfu 0.02%
iter 1134: loss 1.8430, time 76.26ms, mfu 0.02%
iter 1135: loss 1.9807, time 62.18ms, mfu 0.02%
iter 1136: loss 1.9848, time 50.02ms, mfu 0.02%
iter 1137: loss 1.9448, time 96.94ms, mfu 0.02%
iter 1138: loss 2.0107, time 60.15ms, mfu 0.02%
iter 1139: loss 2.0077, time 58.64ms, mfu 0.02%
iter 1140: loss 1.9690, time 48.06ms, mfu 0.02%
iter 1141: loss 2.0303, time 74.94ms, mfu 0.02%
iter 1142: loss 1.8694, time 143.85ms, mfu 0.02%
iter 1143: loss 1.9680, time 133.66ms, mfu 0.02%
iter 1144: loss 1.8829, time 224.78ms, mfu 0.02%
iter 1145: loss 1.9843, time 106.32ms, mfu 0.02%
iter 1146: loss 1.8586, time 84.79ms, mfu 0.02%
iter 1147: loss 1.9180, time 96.01ms, mfu 0.01%
iter 1148: loss 1.9007, time 125.23ms, mfu 0.01%
iter 1149: loss 1.9126, time 209.53ms, mfu 0.01%
iter 1150: loss 1.9558, time 1238.25ms, mfu 0.01%
iter 1151: loss 1.9550, time 675.90ms, mfu 0.01%
iter 1152: loss 2.0435, time 86.45ms, mfu 0.01%
iter 1153: loss 1.9602, time 73.23ms, mfu 0.01%
iter 1154: loss 1.9603, time 381.70ms, mfu 0.01%
iter 1155: loss 1.9797, time 120.78ms, mfu 0.01%
iter 1156: loss 1.9090, time 104.29ms, mfu 0.01%
iter 1157: loss 1.9850, time 85.57ms, mfu 0.01%
iter 1158: loss 2.0127, time 73.23ms, mfu 0.01%
iter 1159: loss 1.9794, time 58.28ms, mfu 0.01%
iter 1160: loss 2.0075, time 84.14ms, mfu 0.01%
iter 1161: loss 2.0370, time 63.30ms, mfu 0.01%
iter 1162: loss 1.9883, time 60.23ms, mfu 0.01%
iter 1163: loss 2.0064, time 69.86ms, mfu 0.02%
iter 1164: loss 2.0182, time 105.96ms, mfu 0.01%
iter 1165: loss 1.8655, time 206.83ms, mfu 0.01%
iter 1166: loss 1.8017, time 116.23ms, mfu 0.01%
iter 1167: loss 1.8910, time 72.92ms, mfu 0.01%
iter 1168: loss 1.7690, time 55.96ms, mfu 0.01%
iter 1169: loss 1.9658, time 66.98ms, mfu 0.02%
iter 1170: loss 1.9272, time 86.29ms, mfu 0.02%
iter 1171: loss 1.9648, time 85.39ms, mfu 0.02%
iter 1172: loss 1.8443, time 85.17ms, mfu 0.02%
iter 1173: loss 1.9639, time 72.94ms, mfu 0.02%
iter 1174: loss 1.9477, time 67.85ms, mfu 0.02%
iter 1175: loss 1.8315, time 125.77ms, mfu 0.02%
iter 1176: loss 1.9440, time 125.14ms, mfu 0.01%
iter 1177: loss 1.9990, time 120.59ms, mfu 0.01%
iter 1178: loss 1.9571, time 82.20ms, mfu 0.01%
iter 1179: loss 1.8974, time 62.33ms, mfu 0.01%
iter 1180: loss 2.0595, time 94.91ms, mfu 0.01%
iter 1181: loss 1.9522, time 55.14ms, mfu 0.02%
iter 1182: loss 1.9216, time 43.66ms, mfu 0.02%
iter 1183: loss 1.9478, time 41.01ms, mfu 0.02%
iter 1184: loss 1.9208, time 70.19ms, mfu 0.02%
iter 1185: loss 2.0696, time 67.68ms, mfu 0.02%
iter 1186: loss 1.9023, time 170.22ms, mfu 0.02%
iter 1187: loss 1.8995, time 843.01ms, mfu 0.02%
iter 1188: loss 1.9731, time 346.97ms, mfu 0.01%
iter 1189: loss 1.9414, time 159.28ms, mfu 0.01%
iter 1190: loss 1.9560, time 201.78ms, mfu 0.01%
iter 1191: loss 2.0242, time 198.39ms, mfu 0.01%
iter 1192: loss 1.9800, time 474.65ms, mfu 0.01%
iter 1193: loss 1.9320, time 214.97ms, mfu 0.01%
iter 1194: loss 1.9850, time 127.36ms, mfu 0.01%
iter 1195: loss 1.9885, time 140.16ms, mfu 0.01%
iter 1196: loss 1.9300, time 178.16ms, mfu 0.01%
iter 1197: loss 1.9234, time 327.50ms, mfu 0.01%
iter 1198: loss 1.8685, time 83.84ms, mfu 0.01%
iter 1199: loss 1.8680, time 82.73ms, mfu 0.01%
iter 1200: loss 1.9533, time 70.30ms, mfu 0.01%
iter 1201: loss 1.9166, time 56.59ms, mfu 0.01%
iter 1202: loss 1.9262, time 103.67ms, mfu 0.01%
iter 1203: loss 1.8414, time 83.59ms, mfu 0.01%
iter 1204: loss 1.9662, time 85.56ms, mfu 0.01%
iter 1205: loss 1.8065, time 70.90ms, mfu 0.01%
iter 1206: loss 1.8671, time 81.45ms, mfu 0.01%
iter 1207: loss 1.9174, time 103.57ms, mfu 0.01%
iter 1208: loss 1.8482, time 82.29ms, mfu 0.01%
iter 1209: loss 1.9081, time 78.88ms, mfu 0.01%
iter 1210: loss 1.9181, time 64.97ms, mfu 0.01%
iter 1211: loss 1.9738, time 55.14ms, mfu 0.02%
iter 1212: loss 1.9848, time 60.97ms, mfu 0.02%
iter 1213: loss 1.9242, time 52.83ms, mfu 0.02%
iter 1214: loss 1.8897, time 71.09ms, mfu 0.02%
iter 1215: loss 2.0222, time 85.31ms, mfu 0.02%
iter 1216: loss 1.9389, time 63.51ms, mfu 0.02%
iter 1217: loss 1.8715, time 49.79ms, mfu 0.02%
iter 1218: loss 1.8319, time 56.08ms, mfu 0.02%
iter 1219: loss 2.0098, time 56.24ms, mfu 0.02%
iter 1220: loss 1.8898, time 94.40ms, mfu 0.02%
iter 1221: loss 1.8818, time 257.87ms, mfu 0.02%
iter 1222: loss 1.7452, time 118.90ms, mfu 0.02%
iter 1223: loss 1.8916, time 53.51ms, mfu 0.02%
iter 1224: loss 1.9362, time 72.54ms, mfu 0.02%
iter 1225: loss 1.9277, time 62.87ms, mfu 0.02%
iter 1226: loss 1.8854, time 81.31ms, mfu 0.02%
iter 1227: loss 1.9490, time 162.79ms, mfu 0.02%
iter 1228: loss 1.8277, time 50.26ms, mfu 0.02%
iter 1229: loss 1.7937, time 74.72ms, mfu 0.02%
iter 1230: loss 1.9035, time 57.84ms, mfu 0.02%
iter 1231: loss 1.8742, time 53.93ms, mfu 0.02%
iter 1232: loss 1.9752, time 81.29ms, mfu 0.02%
iter 1233: loss 1.9890, time 163.81ms, mfu 0.02%
iter 1234: loss 1.9082, time 110.31ms, mfu 0.02%
iter 1235: loss 1.7999, time 82.25ms, mfu 0.02%
iter 1236: loss 1.9449, time 68.59ms, mfu 0.02%
iter 1237: loss 1.9138, time 438.45ms, mfu 0.02%
iter 1238: loss 1.8073, time 650.11ms, mfu 0.01%
iter 1239: loss 1.9190, time 518.14ms, mfu 0.01%
iter 1240: loss 1.8668, time 474.65ms, mfu 0.01%
iter 1241: loss 1.8846, time 268.00ms, mfu 0.01%
iter 1242: loss 1.8601, time 186.96ms, mfu 0.01%
iter 1243: loss 1.9524, time 353.64ms, mfu 0.01%
iter 1244: loss 1.8929, time 123.66ms, mfu 0.01%
iter 1245: loss 1.7851, time 80.68ms, mfu 0.01%
iter 1246: loss 1.8750, time 52.83ms, mfu 0.01%
iter 1247: loss 1.9050, time 130.83ms, mfu 0.01%
iter 1248: loss 1.9501, time 183.14ms, mfu 0.01%
iter 1249: loss 1.8222, time 379.91ms, mfu 0.01%
step 1250: train loss 1.8756, val loss 2.0089
saving checkpoint to out-shakespeare-char
iter 1250: loss 1.8472, time 1176.91ms, mfu 0.01%
iter 1251: loss 1.9505, time 56.64ms, mfu 0.01%
iter 1252: loss 2.0043, time 73.16ms, mfu 0.01%
iter 1253: loss 1.7978, time 47.66ms, mfu 0.01%
iter 1254: loss 1.9211, time 86.94ms, mfu 0.01%
iter 1255: loss 1.8505, time 90.23ms, mfu 0.01%
iter 1256: loss 1.9438, time 83.47ms, mfu 0.01%
iter 1257: loss 1.8914, time 227.43ms, mfu 0.01%
iter 1258: loss 1.9125, time 164.48ms, mfu 0.01%
iter 1259: loss 1.8568, time 322.85ms, mfu 0.01%
iter 1260: loss 1.8822, time 191.62ms, mfu 0.01%
iter 1261: loss 1.9794, time 385.86ms, mfu 0.01%
iter 1262: loss 1.8935, time 157.14ms, mfu 0.01%
iter 1263: loss 1.9714, time 124.38ms, mfu 0.01%
iter 1264: loss 1.8707, time 111.90ms, mfu 0.01%
iter 1265: loss 1.8929, time 164.22ms, mfu 0.01%
iter 1266: loss 1.8141, time 241.55ms, mfu 0.01%
iter 1267: loss 1.8904, time 158.51ms, mfu 0.01%
iter 1268: loss 1.9340, time 151.79ms, mfu 0.01%
iter 1269: loss 1.9194, time 141.11ms, mfu 0.01%
iter 1270: loss 1.9168, time 117.54ms, mfu 0.01%
iter 1271: loss 1.7886, time 382.78ms, mfu 0.01%
iter 1272: loss 1.8410, time 990.11ms, mfu 0.01%
iter 1273: loss 1.8824, time 304.78ms, mfu 0.01%
iter 1274: loss 1.8806, time 366.88ms, mfu 0.01%
iter 1275: loss 1.8993, time 199.59ms, mfu 0.01%
iter 1276: loss 1.6987, time 267.75ms, mfu 0.01%
iter 1277: loss 1.9277, time 274.51ms, mfu 0.01%
iter 1278: loss 1.8362, time 176.38ms, mfu 0.01%
iter 1279: loss 1.8692, time 172.24ms, mfu 0.01%
iter 1280: loss 1.7214, time 338.33ms, mfu 0.01%
iter 1281: loss 1.9492, time 585.25ms, mfu 0.01%
iter 1282: loss 1.9036, time 116.84ms, mfu 0.01%
iter 1283: loss 1.8903, time 109.65ms, mfu 0.01%
iter 1284: loss 1.8991, time 81.52ms, mfu 0.01%
iter 1285: loss 1.8804, time 98.20ms, mfu 0.01%
iter 1286: loss 1.9742, time 74.58ms, mfu 0.01%
iter 1287: loss 1.8957, time 93.08ms, mfu 0.01%
iter 1288: loss 1.7816, time 73.48ms, mfu 0.01%
iter 1289: loss 1.9166, time 70.48ms, mfu 0.01%
iter 1290: loss 1.9213, time 72.53ms, mfu 0.01%
iter 1291: loss 1.9487, time 51.26ms, mfu 0.01%
iter 1292: loss 1.8637, time 54.45ms, mfu 0.01%
iter 1293: loss 1.9852, time 86.63ms, mfu 0.01%
iter 1294: loss 1.8977, time 66.09ms, mfu 0.01%
iter 1295: loss 1.8581, time 66.85ms, mfu 0.02%
iter 1296: loss 1.8894, time 65.41ms, mfu 0.02%
iter 1297: loss 1.9383, time 82.99ms, mfu 0.02%
iter 1298: loss 1.8687, time 325.05ms, mfu 0.01%
iter 1299: loss 2.0321, time 102.57ms, mfu 0.01%
iter 1300: loss 1.9599, time 78.82ms, mfu 0.01%
iter 1301: loss 1.8696, time 61.98ms, mfu 0.02%
iter 1302: loss 1.8468, time 40.72ms, mfu 0.02%
iter 1303: loss 1.9068, time 59.58ms, mfu 0.02%
iter 1304: loss 1.8604, time 74.96ms, mfu 0.02%
iter 1305: loss 1.9658, time 57.33ms, mfu 0.02%
iter 1306: loss 1.9136, time 50.56ms, mfu 0.02%
iter 1307: loss 1.8064, time 49.76ms, mfu 0.02%
iter 1308: loss 1.9828, time 57.92ms, mfu 0.02%
iter 1309: loss 1.9513, time 65.72ms, mfu 0.02%
iter 1310: loss 1.8802, time 81.07ms, mfu 0.02%
iter 1311: loss 1.9208, time 77.96ms, mfu 0.02%
iter 1312: loss 1.8707, time 237.78ms, mfu 0.02%
iter 1313: loss 1.9803, time 221.53ms, mfu 0.02%
iter 1314: loss 1.8814, time 152.73ms, mfu 0.02%
iter 1315: loss 1.9117, time 464.06ms, mfu 0.01%
iter 1316: loss 1.8104, time 463.82ms, mfu 0.01%
iter 1317: loss 1.8911, time 471.53ms, mfu 0.01%
iter 1318: loss 1.8885, time 520.55ms, mfu 0.01%
iter 1319: loss 1.9571, time 208.24ms, mfu 0.01%
iter 1320: loss 1.9631, time 277.22ms, mfu 0.01%
iter 1321: loss 1.8718, time 180.19ms, mfu 0.01%
iter 1322: loss 2.0186, time 100.99ms, mfu 0.01%
iter 1323: loss 1.8636, time 102.88ms, mfu 0.01%
iter 1324: loss 1.8920, time 77.44ms, mfu 0.01%
iter 1325: loss 1.8935, time 187.79ms, mfu 0.01%
iter 1326: loss 1.9010, time 632.47ms, mfu 0.01%
iter 1327: loss 2.0102, time 168.68ms, mfu 0.01%
iter 1328: loss 1.7928, time 82.51ms, mfu 0.01%
iter 1329: loss 1.8508, time 175.39ms, mfu 0.01%
iter 1330: loss 1.9832, time 460.28ms, mfu 0.01%
iter 1331: loss 1.8661, time 284.97ms, mfu 0.01%
iter 1332: loss 1.8195, time 208.01ms, mfu 0.01%
iter 1333: loss 1.8314, time 158.67ms, mfu 0.01%
iter 1334: loss 1.9103, time 118.78ms, mfu 0.01%
iter 1335: loss 1.8740, time 119.72ms, mfu 0.01%
iter 1336: loss 1.9292, time 147.82ms, mfu 0.01%
iter 1337: loss 1.9404, time 240.71ms, mfu 0.01%
iter 1338: loss 1.7941, time 85.82ms, mfu 0.01%
iter 1339: loss 1.8813, time 73.03ms, mfu 0.01%
iter 1340: loss 1.9444, time 71.87ms, mfu 0.01%
iter 1341: loss 1.9021, time 60.15ms, mfu 0.01%
iter 1342: loss 1.9020, time 39.13ms, mfu 0.01%
iter 1343: loss 1.8683, time 59.43ms, mfu 0.01%
iter 1344: loss 1.8009, time 85.04ms, mfu 0.01%
iter 1345: loss 1.9014, time 57.75ms, mfu 0.02%
iter 1346: loss 1.8565, time 59.18ms, mfu 0.02%
iter 1347: loss 1.9952, time 87.13ms, mfu 0.02%
iter 1348: loss 1.8950, time 67.58ms, mfu 0.02%
iter 1349: loss 1.8574, time 140.81ms, mfu 0.02%
iter 1350: loss 1.8367, time 127.68ms, mfu 0.01%
iter 1351: loss 1.7387, time 85.18ms, mfu 0.01%
iter 1352: loss 1.8476, time 74.11ms, mfu 0.02%
iter 1353: loss 1.9139, time 86.74ms, mfu 0.02%
iter 1354: loss 1.9258, time 81.20ms, mfu 0.02%
iter 1355: loss 1.8739, time 70.99ms, mfu 0.02%
iter 1356: loss 1.8640, time 107.73ms, mfu 0.02%
iter 1357: loss 1.7721, time 119.99ms, mfu 0.01%
iter 1358: loss 1.8393, time 108.13ms, mfu 0.01%
iter 1359: loss 1.9871, time 143.90ms, mfu 0.01%
iter 1360: loss 1.8941, time 147.84ms, mfu 0.01%
iter 1361: loss 1.8890, time 112.41ms, mfu 0.01%
iter 1362: loss 1.8848, time 95.88ms, mfu 0.01%
iter 1363: loss 1.9245, time 309.14ms, mfu 0.01%
iter 1364: loss 1.8883, time 175.81ms, mfu 0.01%
iter 1365: loss 1.9321, time 735.33ms, mfu 0.01%
iter 1366: loss 1.9759, time 340.39ms, mfu 0.01%
iter 1367: loss 1.7825, time 220.14ms, mfu 0.01%
iter 1368: loss 1.8662, time 105.99ms, mfu 0.01%
iter 1369: loss 1.8926, time 101.07ms, mfu 0.01%
iter 1370: loss 1.8958, time 95.55ms, mfu 0.01%
iter 1371: loss 1.9527, time 113.54ms, mfu 0.01%
iter 1372: loss 1.9104, time 60.99ms, mfu 0.01%
iter 1373: loss 1.8593, time 80.81ms, mfu 0.01%
iter 1374: loss 1.9066, time 74.75ms, mfu 0.01%
iter 1375: loss 1.8517, time 58.33ms, mfu 0.01%
iter 1376: loss 1.7638, time 90.38ms, mfu 0.01%
iter 1377: loss 1.8865, time 107.27ms, mfu 0.01%
iter 1378: loss 1.8301, time 123.29ms, mfu 0.01%
iter 1379: loss 1.9391, time 101.96ms, mfu 0.01%
iter 1380: loss 1.7734, time 67.73ms, mfu 0.01%
iter 1381: loss 1.9339, time 77.47ms, mfu 0.01%
iter 1382: loss 1.7921, time 58.53ms, mfu 0.01%
iter 1383: loss 1.8849, time 54.49ms, mfu 0.02%
iter 1384: loss 1.8568, time 69.74ms, mfu 0.02%
iter 1385: loss 1.9190, time 71.14ms, mfu 0.02%
iter 1386: loss 1.7977, time 65.44ms, mfu 0.02%
iter 1387: loss 1.8599, time 50.81ms, mfu 0.02%
iter 1388: loss 1.8525, time 87.20ms, mfu 0.02%
iter 1389: loss 1.8533, time 67.33ms, mfu 0.02%
iter 1390: loss 1.9301, time 113.34ms, mfu 0.02%
iter 1391: loss 1.8160, time 103.24ms, mfu 0.02%
iter 1392: loss 1.8530, time 67.49ms, mfu 0.02%
iter 1393: loss 1.9791, time 53.58ms, mfu 0.02%
iter 1394: loss 1.8913, time 100.77ms, mfu 0.02%
iter 1395: loss 1.8677, time 85.77ms, mfu 0.02%
iter 1396: loss 1.8882, time 42.19ms, mfu 0.02%
iter 1397: loss 1.8208, time 30.77ms, mfu 0.02%
iter 1398: loss 1.7251, time 36.66ms, mfu 0.02%
iter 1399: loss 1.9319, time 51.76ms, mfu 0.02%
iter 1400: loss 1.8251, time 55.40ms, mfu 0.02%
iter 1401: loss 1.8336, time 47.41ms, mfu 0.02%
iter 1402: loss 1.9545, time 55.89ms, mfu 0.02%
iter 1403: loss 1.8206, time 61.73ms, mfu 0.02%
iter 1404: loss 1.9279, time 53.13ms, mfu 0.02%
iter 1405: loss 1.9249, time 58.59ms, mfu 0.02%
iter 1406: loss 1.8807, time 83.22ms, mfu 0.02%
iter 1407: loss 1.9173, time 86.14ms, mfu 0.02%
iter 1408: loss 1.8707, time 65.51ms, mfu 0.02%
iter 1409: loss 1.9065, time 175.66ms, mfu 0.02%
iter 1410: loss 1.8992, time 524.14ms, mfu 0.02%
iter 1411: loss 1.7874, time 329.71ms, mfu 0.02%
iter 1412: loss 1.8687, time 387.92ms, mfu 0.02%
iter 1413: loss 1.8950, time 227.04ms, mfu 0.01%
iter 1414: loss 1.8444, time 192.86ms, mfu 0.01%
iter 1415: loss 1.8862, time 131.72ms, mfu 0.01%
iter 1416: loss 1.8390, time 213.65ms, mfu 0.01%
iter 1417: loss 1.8496, time 211.54ms, mfu 0.01%
iter 1418: loss 1.9114, time 137.71ms, mfu 0.01%
iter 1419: loss 1.8822, time 156.93ms, mfu 0.01%
iter 1420: loss 1.8308, time 176.97ms, mfu 0.01%
iter 1421: loss 1.8732, time 147.31ms, mfu 0.01%
iter 1422: loss 1.8949, time 183.02ms, mfu 0.01%
iter 1423: loss 1.8320, time 174.80ms, mfu 0.01%
iter 1424: loss 1.7847, time 105.12ms, mfu 0.01%
iter 1425: loss 1.8736, time 114.19ms, mfu 0.01%
iter 1426: loss 1.9243, time 124.65ms, mfu 0.01%
iter 1427: loss 1.8880, time 120.89ms, mfu 0.01%
iter 1428: loss 1.8604, time 127.86ms, mfu 0.01%
iter 1429: loss 1.9600, time 104.79ms, mfu 0.01%
iter 1430: loss 1.8750, time 81.59ms, mfu 0.01%
iter 1431: loss 1.8466, time 157.80ms, mfu 0.01%
iter 1432: loss 2.0068, time 104.27ms, mfu 0.01%
iter 1433: loss 1.8885, time 74.58ms, mfu 0.01%
iter 1434: loss 1.9159, time 45.15ms, mfu 0.01%
iter 1435: loss 1.8457, time 48.48ms, mfu 0.01%
iter 1436: loss 1.9120, time 63.09ms, mfu 0.01%
iter 1437: loss 1.8213, time 51.41ms, mfu 0.02%
iter 1438: loss 1.9079, time 79.15ms, mfu 0.02%
iter 1439: loss 1.7653, time 86.20ms, mfu 0.02%
iter 1440: loss 1.7765, time 59.91ms, mfu 0.02%
iter 1441: loss 1.7510, time 56.43ms, mfu 0.02%
iter 1442: loss 1.8549, time 47.41ms, mfu 0.02%
iter 1443: loss 1.7976, time 83.24ms, mfu 0.02%
iter 1444: loss 1.8192, time 85.57ms, mfu 0.02%
iter 1445: loss 1.8632, time 135.77ms, mfu 0.02%
iter 1446: loss 1.8890, time 370.29ms, mfu 0.02%
iter 1447: loss 1.8887, time 119.93ms, mfu 0.01%
iter 1448: loss 2.0332, time 150.41ms, mfu 0.01%
iter 1449: loss 1.7804, time 67.80ms, mfu 0.01%
iter 1450: loss 1.8467, time 57.62ms, mfu 0.02%
iter 1451: loss 1.8490, time 67.00ms, mfu 0.02%
iter 1452: loss 1.8041, time 70.15ms, mfu 0.02%
iter 1453: loss 1.8066, time 75.96ms, mfu 0.02%
iter 1454: loss 1.7856, time 69.36ms, mfu 0.02%
iter 1455: loss 1.9288, time 84.84ms, mfu 0.02%
iter 1456: loss 1.7772, time 83.34ms, mfu 0.02%
iter 1457: loss 1.8652, time 99.41ms, mfu 0.02%
iter 1458: loss 1.7608, time 384.26ms, mfu 0.01%
iter 1459: loss 1.8071, time 310.40ms, mfu 0.01%
iter 1460: loss 1.8346, time 569.69ms, mfu 0.01%
iter 1461: loss 1.8516, time 276.33ms, mfu 0.01%
iter 1462: loss 1.8396, time 162.50ms, mfu 0.01%
iter 1463: loss 1.8830, time 435.83ms, mfu 0.01%
iter 1464: loss 1.9313, time 224.66ms, mfu 0.01%
iter 1465: loss 1.8594, time 105.13ms, mfu 0.01%
iter 1466: loss 1.8750, time 114.68ms, mfu 0.01%
iter 1467: loss 1.8087, time 85.24ms, mfu 0.01%
iter 1468: loss 1.7728, time 126.05ms, mfu 0.01%
iter 1469: loss 1.8967, time 101.01ms, mfu 0.01%
iter 1470: loss 1.8773, time 77.21ms, mfu 0.01%
iter 1471: loss 1.8480, time 93.59ms, mfu 0.01%
iter 1472: loss 1.8651, time 177.69ms, mfu 0.01%
iter 1473: loss 1.8508, time 72.80ms, mfu 0.01%
iter 1474: loss 1.8673, time 49.46ms, mfu 0.01%
iter 1475: loss 1.9003, time 45.55ms, mfu 0.01%
iter 1476: loss 2.0827, time 72.58ms, mfu 0.01%
iter 1477: loss 1.7993, time 37.31ms, mfu 0.02%
iter 1478: loss 1.8796, time 54.36ms, mfu 0.02%
iter 1479: loss 1.8845, time 83.90ms, mfu 0.02%
iter 1480: loss 1.8389, time 187.09ms, mfu 0.02%
iter 1481: loss 1.7949, time 49.21ms, mfu 0.02%
iter 1482: loss 1.7822, time 42.39ms, mfu 0.02%
iter 1483: loss 1.8141, time 41.61ms, mfu 0.02%
iter 1484: loss 1.8112, time 95.19ms, mfu 0.02%
iter 1485: loss 1.7876, time 190.85ms, mfu 0.02%
iter 1486: loss 1.8575, time 128.02ms, mfu 0.02%
iter 1487: loss 1.8741, time 129.60ms, mfu 0.02%
iter 1488: loss 1.7862, time 155.70ms, mfu 0.02%
iter 1489: loss 1.9402, time 308.69ms, mfu 0.01%
iter 1490: loss 1.8105, time 119.82ms, mfu 0.01%
iter 1491: loss 1.8227, time 132.11ms, mfu 0.01%
iter 1492: loss 1.7702, time 160.20ms, mfu 0.01%
iter 1493: loss 1.7748, time 123.93ms, mfu 0.01%
iter 1494: loss 1.8848, time 64.08ms, mfu 0.01%
iter 1495: loss 1.7646, time 50.83ms, mfu 0.01%
iter 1496: loss 1.7851, time 59.07ms, mfu 0.02%
iter 1497: loss 1.8713, time 133.56ms, mfu 0.01%
iter 1498: loss 1.7788, time 88.61ms, mfu 0.01%
iter 1499: loss 1.8476, time 83.23ms, mfu 0.01%
step 1500: train loss 1.8557, val loss 1.9225
saving checkpoint to out-shakespeare-char
iter 1500: loss 1.8624, time 2809.29ms, mfu 0.01%
iter 1501: loss 1.9029, time 333.96ms, mfu 0.01%
iter 1502: loss 1.8334, time 105.67ms, mfu 0.01%
iter 1503: loss 1.8723, time 73.68ms, mfu 0.01%
iter 1504: loss 1.8613, time 87.21ms, mfu 0.01%
iter 1505: loss 1.8844, time 71.73ms, mfu 0.01%
iter 1506: loss 1.7501, time 50.08ms, mfu 0.01%
iter 1507: loss 1.8751, time 86.13ms, mfu 0.01%
iter 1508: loss 2.0147, time 87.25ms, mfu 0.01%
iter 1509: loss 1.8591, time 78.13ms, mfu 0.01%
iter 1510: loss 1.7505, time 65.43ms, mfu 0.02%
iter 1511: loss 1.8415, time 57.78ms, mfu 0.02%
iter 1512: loss 1.7407, time 57.69ms, mfu 0.02%
iter 1513: loss 1.7791, time 66.24ms, mfu 0.02%
iter 1514: loss 1.8457, time 56.54ms, mfu 0.02%
iter 1515: loss 1.8212, time 88.76ms, mfu 0.02%
iter 1516: loss 1.8134, time 110.47ms, mfu 0.02%
iter 1517: loss 1.7699, time 83.05ms, mfu 0.02%
iter 1518: loss 1.8516, time 63.50ms, mfu 0.02%
iter 1519: loss 1.8508, time 58.19ms, mfu 0.02%
iter 1520: loss 1.8912, time 45.93ms, mfu 0.02%
iter 1521: loss 1.7793, time 60.43ms, mfu 0.02%
iter 1522: loss 1.8573, time 46.42ms, mfu 0.02%
iter 1523: loss 1.8069, time 75.62ms, mfu 0.02%
iter 1524: loss 1.7402, time 52.50ms, mfu 0.02%
iter 1525: loss 1.8282, time 60.48ms, mfu 0.02%
iter 1526: loss 1.8168, time 44.54ms, mfu 0.02%
iter 1527: loss 1.7843, time 52.33ms, mfu 0.02%
iter 1528: loss 1.8344, time 46.09ms, mfu 0.02%
iter 1529: loss 1.8107, time 63.21ms, mfu 0.02%
iter 1530: loss 1.8465, time 52.59ms, mfu 0.02%
iter 1531: loss 1.8449, time 76.01ms, mfu 0.02%
iter 1532: loss 1.8415, time 78.43ms, mfu 0.02%
iter 1533: loss 1.8430, time 73.58ms, mfu 0.02%
iter 1534: loss 1.8973, time 51.29ms, mfu 0.02%
iter 1535: loss 1.7893, time 58.59ms, mfu 0.02%
iter 1536: loss 1.8587, time 43.13ms, mfu 0.02%
iter 1537: loss 1.9075, time 28.85ms, mfu 0.02%
iter 1538: loss 1.8520, time 49.52ms, mfu 0.02%
iter 1539: loss 1.8734, time 52.52ms, mfu 0.02%
iter 1540: loss 1.7848, time 43.69ms, mfu 0.02%
iter 1541: loss 1.8395, time 74.14ms, mfu 0.02%
iter 1542: loss 1.7912, time 44.80ms, mfu 0.02%
iter 1543: loss 1.9071, time 35.55ms, mfu 0.03%
iter 1544: loss 1.8089, time 66.01ms, mfu 0.02%
iter 1545: loss 1.8766, time 39.11ms, mfu 0.03%
iter 1546: loss 1.7501, time 64.12ms, mfu 0.03%
iter 1547: loss 1.8623, time 62.26ms, mfu 0.02%
iter 1548: loss 1.8256, time 55.58ms, mfu 0.02%
iter 1549: loss 1.8087, time 118.46ms, mfu 0.02%
iter 1550: loss 1.8736, time 153.60ms, mfu 0.02%
iter 1551: loss 1.7196, time 114.60ms, mfu 0.02%
iter 1552: loss 1.8209, time 56.78ms, mfu 0.02%
iter 1553: loss 1.8825, time 44.43ms, mfu 0.02%
iter 1554: loss 1.7125, time 72.85ms, mfu 0.02%
iter 1555: loss 1.8519, time 55.91ms, mfu 0.02%
iter 1556: loss 1.7490, time 64.28ms, mfu 0.02%
iter 1557: loss 1.8797, time 119.31ms, mfu 0.02%
iter 1558: loss 1.7944, time 60.06ms, mfu 0.02%
iter 1559: loss 1.8864, time 128.48ms, mfu 0.02%
iter 1560: loss 1.8491, time 83.77ms, mfu 0.02%
iter 1561: loss 1.7478, time 109.40ms, mfu 0.02%
iter 1562: loss 1.7721, time 127.34ms, mfu 0.02%
iter 1563: loss 1.7795, time 149.96ms, mfu 0.02%
iter 1564: loss 1.7300, time 475.67ms, mfu 0.02%
iter 1565: loss 1.7812, time 240.77ms, mfu 0.01%
iter 1566: loss 1.8205, time 141.16ms, mfu 0.01%
iter 1567: loss 1.7802, time 120.82ms, mfu 0.01%
iter 1568: loss 1.7921, time 67.10ms, mfu 0.01%
iter 1569: loss 1.8613, time 60.32ms, mfu 0.01%
iter 1570: loss 1.8325, time 73.72ms, mfu 0.01%
iter 1571: loss 1.8301, time 56.09ms, mfu 0.02%
iter 1572: loss 1.8649, time 55.62ms, mfu 0.02%
iter 1573: loss 1.8089, time 80.87ms, mfu 0.02%
iter 1574: loss 1.6946, time 81.06ms, mfu 0.02%
iter 1575: loss 1.7825, time 58.36ms, mfu 0.02%
iter 1576: loss 1.8883, time 63.79ms, mfu 0.02%
iter 1577: loss 1.7559, time 82.26ms, mfu 0.02%
iter 1578: loss 1.7638, time 67.54ms, mfu 0.02%
iter 1579: loss 1.8210, time 58.95ms, mfu 0.02%
iter 1580: loss 1.7281, time 49.51ms, mfu 0.02%
iter 1581: loss 1.8286, time 38.06ms, mfu 0.02%
iter 1582: loss 1.8387, time 41.73ms, mfu 0.02%
iter 1583: loss 1.7638, time 50.62ms, mfu 0.02%
iter 1584: loss 1.7144, time 47.57ms, mfu 0.02%
iter 1585: loss 1.8740, time 61.02ms, mfu 0.02%
iter 1586: loss 1.8780, time 42.49ms, mfu 0.02%
iter 1587: loss 1.9013, time 40.16ms, mfu 0.02%
iter 1588: loss 1.8361, time 60.47ms, mfu 0.02%
iter 1589: loss 1.7214, time 35.22ms, mfu 0.02%
iter 1590: loss 1.7680, time 54.25ms, mfu 0.02%
iter 1591: loss 1.8756, time 49.47ms, mfu 0.02%
iter 1592: loss 1.6822, time 58.27ms, mfu 0.02%
iter 1593: loss 1.8340, time 50.40ms, mfu 0.02%
iter 1594: loss 1.7960, time 71.73ms, mfu 0.02%
iter 1595: loss 1.8945, time 48.49ms, mfu 0.02%
iter 1596: loss 1.8207, time 66.40ms, mfu 0.02%
iter 1597: loss 1.8352, time 70.65ms, mfu 0.02%
iter 1598: loss 1.7969, time 51.82ms, mfu 0.02%
iter 1599: loss 1.7746, time 29.73ms, mfu 0.03%
iter 1600: loss 1.7808, time 27.92ms, mfu 0.03%
iter 1601: loss 1.7328, time 31.71ms, mfu 0.03%
iter 1602: loss 1.8331, time 30.44ms, mfu 0.03%
iter 1603: loss 1.8316, time 31.46ms, mfu 0.03%
iter 1604: loss 1.8537, time 39.20ms, mfu 0.03%
iter 1605: loss 1.7347, time 31.69ms, mfu 0.03%
iter 1606: loss 1.8569, time 27.55ms, mfu 0.03%
iter 1607: loss 1.8159, time 39.34ms, mfu 0.03%
iter 1608: loss 1.8937, time 41.26ms, mfu 0.03%
iter 1609: loss 1.8270, time 38.89ms, mfu 0.03%
iter 1610: loss 1.8423, time 65.34ms, mfu 0.03%
iter 1611: loss 1.8658, time 76.71ms, mfu 0.03%
iter 1612: loss 1.8421, time 64.33ms, mfu 0.03%
iter 1613: loss 1.6999, time 73.47ms, mfu 0.03%
iter 1614: loss 1.8139, time 54.45ms, mfu 0.03%
iter 1615: loss 1.8105, time 54.63ms, mfu 0.03%
iter 1616: loss 1.8139, time 79.34ms, mfu 0.03%
iter 1617: loss 1.7697, time 274.31ms, mfu 0.02%
iter 1618: loss 1.7595, time 140.25ms, mfu 0.02%
iter 1619: loss 1.7615, time 198.37ms, mfu 0.02%
iter 1620: loss 1.8048, time 145.84ms, mfu 0.02%
iter 1621: loss 1.8572, time 228.08ms, mfu 0.02%
iter 1622: loss 1.8292, time 247.96ms, mfu 0.02%
iter 1623: loss 1.9528, time 107.95ms, mfu 0.02%
iter 1624: loss 1.7806, time 73.06ms, mfu 0.02%
iter 1625: loss 1.7796, time 452.65ms, mfu 0.02%
iter 1626: loss 1.8230, time 138.26ms, mfu 0.01%
iter 1627: loss 1.8743, time 138.03ms, mfu 0.01%
iter 1628: loss 1.7519, time 101.55ms, mfu 0.01%
iter 1629: loss 1.7744, time 68.05ms, mfu 0.01%
iter 1630: loss 1.7679, time 64.31ms, mfu 0.01%
iter 1631: loss 1.8786, time 45.06ms, mfu 0.02%
iter 1632: loss 1.7891, time 45.21ms, mfu 0.02%
iter 1633: loss 1.7429, time 58.69ms, mfu 0.02%
iter 1634: loss 1.7381, time 45.52ms, mfu 0.02%
iter 1635: loss 1.6885, time 65.29ms, mfu 0.02%
iter 1636: loss 1.8223, time 55.55ms, mfu 0.02%
iter 1637: loss 1.8580, time 59.58ms, mfu 0.02%
iter 1638: loss 1.8411, time 49.71ms, mfu 0.02%
iter 1639: loss 1.7807, time 55.38ms, mfu 0.02%
iter 1640: loss 1.8338, time 67.81ms, mfu 0.02%
iter 1641: loss 1.6963, time 79.13ms, mfu 0.02%
iter 1642: loss 1.8068, time 105.88ms, mfu 0.02%
iter 1643: loss 1.8575, time 64.92ms, mfu 0.02%
iter 1644: loss 1.8096, time 47.85ms, mfu 0.02%
iter 1645: loss 1.8229, time 43.61ms, mfu 0.02%
iter 1646: loss 1.8699, time 55.64ms, mfu 0.02%
iter 1647: loss 1.9380, time 43.75ms, mfu 0.02%
iter 1648: loss 1.8300, time 36.31ms, mfu 0.02%
iter 1649: loss 1.7637, time 41.80ms, mfu 0.02%
iter 1650: loss 1.8783, time 34.75ms, mfu 0.03%
iter 1651: loss 1.6766, time 38.50ms, mfu 0.03%
iter 1652: loss 1.8523, time 37.76ms, mfu 0.03%
iter 1653: loss 1.9616, time 48.51ms, mfu 0.03%
iter 1654: loss 1.7503, time 71.91ms, mfu 0.03%
iter 1655: loss 1.8328, time 50.32ms, mfu 0.03%
iter 1656: loss 1.7932, time 76.78ms, mfu 0.02%
iter 1657: loss 1.8028, time 130.08ms, mfu 0.02%
iter 1658: loss 1.7720, time 346.93ms, mfu 0.02%
iter 1659: loss 1.7657, time 152.99ms, mfu 0.02%
iter 1660: loss 1.7460, time 103.18ms, mfu 0.02%
iter 1661: loss 1.8526, time 123.57ms, mfu 0.02%
iter 1662: loss 1.7599, time 108.62ms, mfu 0.02%
iter 1663: loss 1.8023, time 148.78ms, mfu 0.02%
iter 1664: loss 1.8818, time 172.34ms, mfu 0.02%
iter 1665: loss 1.7177, time 154.12ms, mfu 0.02%
iter 1666: loss 1.8367, time 105.63ms, mfu 0.01%
iter 1667: loss 1.8443, time 242.11ms, mfu 0.01%
iter 1668: loss 1.6899, time 122.40ms, mfu 0.01%
iter 1669: loss 1.6838, time 104.01ms, mfu 0.01%
iter 1670: loss 1.8474, time 69.48ms, mfu 0.01%
iter 1671: loss 1.8514, time 66.83ms, mfu 0.01%
iter 1672: loss 1.8078, time 129.91ms, mfu 0.01%
iter 1673: loss 1.8371, time 106.86ms, mfu 0.01%
iter 1674: loss 1.8086, time 88.84ms, mfu 0.01%
iter 1675: loss 1.8085, time 44.52ms, mfu 0.02%
iter 1676: loss 1.7926, time 58.48ms, mfu 0.02%
iter 1677: loss 1.8536, time 47.57ms, mfu 0.02%
iter 1678: loss 1.7910, time 90.05ms, mfu 0.02%
iter 1679: loss 1.8483, time 127.17ms, mfu 0.02%
iter 1680: loss 1.8388, time 79.47ms, mfu 0.02%
iter 1681: loss 1.8637, time 55.78ms, mfu 0.02%
iter 1682: loss 1.7223, time 73.35ms, mfu 0.02%
iter 1683: loss 1.8121, time 74.77ms, mfu 0.02%
iter 1684: loss 1.8058, time 124.72ms, mfu 0.02%
iter 1685: loss 1.7476, time 104.77ms, mfu 0.02%
iter 1686: loss 1.8607, time 58.94ms, mfu 0.02%
iter 1687: loss 1.7972, time 48.23ms, mfu 0.02%
iter 1688: loss 1.7813, time 60.54ms, mfu 0.02%
iter 1689: loss 1.6947, time 62.60ms, mfu 0.02%
iter 1690: loss 1.8558, time 47.94ms, mfu 0.02%
iter 1691: loss 1.8517, time 81.40ms, mfu 0.02%
iter 1692: loss 1.9158, time 49.54ms, mfu 0.02%
iter 1693: loss 1.8096, time 69.24ms, mfu 0.02%
iter 1694: loss 1.8569, time 74.52ms, mfu 0.02%
iter 1695: loss 1.7337, time 43.43ms, mfu 0.02%
iter 1696: loss 1.7687, time 54.19ms, mfu 0.02%
iter 1697: loss 1.7989, time 59.94ms, mfu 0.02%
iter 1698: loss 1.8207, time 99.91ms, mfu 0.02%
iter 1699: loss 1.8542, time 86.20ms, mfu 0.02%
iter 1700: loss 1.7163, time 74.74ms, mfu 0.02%
iter 1701: loss 1.7893, time 90.13ms, mfu 0.02%
iter 1702: loss 1.8696, time 69.26ms, mfu 0.02%
iter 1703: loss 1.8218, time 57.80ms, mfu 0.02%
iter 1704: loss 1.5975, time 51.01ms, mfu 0.02%
iter 1705: loss 1.8014, time 48.83ms, mfu 0.02%
iter 1706: loss 1.7459, time 44.89ms, mfu 0.02%
iter 1707: loss 1.8655, time 58.47ms, mfu 0.02%
iter 1708: loss 1.8093, time 52.91ms, mfu 0.02%
iter 1709: loss 1.7775, time 25.49ms, mfu 0.02%
iter 1710: loss 1.8155, time 35.23ms, mfu 0.03%
iter 1711: loss 1.8890, time 33.51ms, mfu 0.03%
iter 1712: loss 1.9253, time 49.77ms, mfu 0.03%
iter 1713: loss 1.8318, time 44.54ms, mfu 0.03%
iter 1714: loss 1.9152, time 42.66ms, mfu 0.03%
iter 1715: loss 1.8138, time 41.71ms, mfu 0.03%
iter 1716: loss 1.8018, time 73.79ms, mfu 0.03%
iter 1717: loss 1.8206, time 96.76ms, mfu 0.03%
iter 1718: loss 1.7672, time 85.32ms, mfu 0.02%
iter 1719: loss 1.8134, time 97.80ms, mfu 0.02%
iter 1720: loss 1.8219, time 70.60ms, mfu 0.02%
iter 1721: loss 1.8645, time 51.52ms, mfu 0.02%
iter 1722: loss 1.8257, time 88.04ms, mfu 0.02%
iter 1723: loss 1.8010, time 71.00ms, mfu 0.02%
iter 1724: loss 1.7704, time 71.25ms, mfu 0.02%
iter 1725: loss 1.7934, time 91.44ms, mfu 0.02%
iter 1726: loss 1.7738, time 82.17ms, mfu 0.02%
iter 1727: loss 1.8267, time 92.42ms, mfu 0.02%
iter 1728: loss 1.8406, time 75.58ms, mfu 0.02%
iter 1729: loss 1.9355, time 100.34ms, mfu 0.02%
iter 1730: loss 1.8010, time 159.99ms, mfu 0.02%
iter 1731: loss 1.7289, time 153.40ms, mfu 0.02%
iter 1732: loss 1.6900, time 384.47ms, mfu 0.02%
iter 1733: loss 1.8331, time 156.00ms, mfu 0.01%
iter 1734: loss 1.7582, time 86.87ms, mfu 0.01%
iter 1735: loss 1.7563, time 348.07ms, mfu 0.01%
iter 1736: loss 1.8971, time 355.83ms, mfu 0.01%
iter 1737: loss 1.7855, time 874.03ms, mfu 0.01%
iter 1738: loss 1.7462, time 134.37ms, mfu 0.01%
iter 1739: loss 1.7415, time 444.96ms, mfu 0.01%
iter 1740: loss 1.7515, time 396.95ms, mfu 0.01%
iter 1741: loss 1.7446, time 318.72ms, mfu 0.01%
iter 1742: loss 1.8519, time 170.65ms, mfu 0.01%
iter 1743: loss 1.8005, time 385.44ms, mfu 0.01%
iter 1744: loss 1.7608, time 112.97ms, mfu 0.01%
iter 1745: loss 1.7233, time 87.15ms, mfu 0.01%
iter 1746: loss 1.7781, time 70.56ms, mfu 0.01%
iter 1747: loss 1.6983, time 79.31ms, mfu 0.01%
iter 1748: loss 1.8040, time 61.88ms, mfu 0.01%
iter 1749: loss 1.7471, time 87.03ms, mfu 0.01%
step 1750: train loss 1.7790, val loss 1.8921
saving checkpoint to out-shakespeare-char
iter 1750: loss 1.8041, time 910.04ms, mfu 0.01%
iter 1751: loss 1.9559, time 54.23ms, mfu 0.01%
iter 1752: loss 1.8112, time 51.26ms, mfu 0.01%
iter 1753: loss 1.6835, time 79.27ms, mfu 0.01%
iter 1754: loss 1.8415, time 57.14ms, mfu 0.01%
iter 1755: loss 1.8036, time 104.43ms, mfu 0.01%
iter 1756: loss 1.7677, time 73.53ms, mfu 0.01%
iter 1757: loss 1.7190, time 98.06ms, mfu 0.01%
iter 1758: loss 1.7417, time 73.17ms, mfu 0.01%
iter 1759: loss 1.7732, time 30.10ms, mfu 0.02%
iter 1760: loss 1.6994, time 23.79ms, mfu 0.02%
iter 1761: loss 1.7389, time 168.29ms, mfu 0.02%
iter 1762: loss 1.7722, time 98.21ms, mfu 0.02%
iter 1763: loss 1.8943, time 63.35ms, mfu 0.02%
iter 1764: loss 1.8158, time 53.61ms, mfu 0.02%
iter 1765: loss 1.7328, time 139.12ms, mfu 0.02%
iter 1766: loss 1.8004, time 100.31ms, mfu 0.02%
iter 1767: loss 1.8424, time 179.56ms, mfu 0.02%
iter 1768: loss 1.8857, time 265.95ms, mfu 0.02%
iter 1769: loss 1.7644, time 195.31ms, mfu 0.01%
iter 1770: loss 1.6505, time 210.67ms, mfu 0.01%
iter 1771: loss 1.7699, time 100.73ms, mfu 0.01%
iter 1772: loss 1.7587, time 296.69ms, mfu 0.01%
iter 1773: loss 1.8406, time 168.49ms, mfu 0.01%
iter 1774: loss 1.7990, time 102.02ms, mfu 0.01%
iter 1775: loss 1.7889, time 401.93ms, mfu 0.01%
iter 1776: loss 1.6292, time 333.74ms, mfu 0.01%
iter 1777: loss 1.8156, time 107.83ms, mfu 0.01%
iter 1778: loss 1.7504, time 111.47ms, mfu 0.01%
iter 1779: loss 1.9579, time 178.90ms, mfu 0.01%
iter 1780: loss 1.7315, time 295.36ms, mfu 0.01%
iter 1781: loss 1.8403, time 355.78ms, mfu 0.01%
iter 1782: loss 1.9166, time 528.80ms, mfu 0.01%
iter 1783: loss 1.7503, time 288.61ms, mfu 0.01%
iter 1784: loss 1.8315, time 629.02ms, mfu 0.01%
iter 1785: loss 1.7967, time 122.67ms, mfu 0.01%
iter 1786: loss 1.7845, time 134.06ms, mfu 0.01%
iter 1787: loss 1.8225, time 231.69ms, mfu 0.01%
iter 1788: loss 1.7811, time 145.60ms, mfu 0.01%
iter 1789: loss 1.7647, time 92.02ms, mfu 0.01%
iter 1790: loss 1.7741, time 62.70ms, mfu 0.01%
iter 1791: loss 1.7642, time 71.30ms, mfu 0.01%
iter 1792: loss 1.8247, time 78.73ms, mfu 0.01%
iter 1793: loss 1.8432, time 44.01ms, mfu 0.01%
iter 1794: loss 1.7787, time 66.91ms, mfu 0.01%
iter 1795: loss 1.7685, time 132.77ms, mfu 0.01%
iter 1796: loss 1.8958, time 94.67ms, mfu 0.01%
iter 1797: loss 1.7584, time 104.00ms, mfu 0.01%
iter 1798: loss 1.7609, time 90.52ms, mfu 0.01%
iter 1799: loss 1.7328, time 52.22ms, mfu 0.01%
iter 1800: loss 1.8415, time 64.61ms, mfu 0.01%
iter 1801: loss 1.8189, time 46.13ms, mfu 0.02%
iter 1802: loss 1.8043, time 61.56ms, mfu 0.02%
iter 1803: loss 1.6580, time 72.21ms, mfu 0.02%
iter 1804: loss 1.8217, time 65.08ms, mfu 0.02%
iter 1805: loss 1.7127, time 68.63ms, mfu 0.02%
iter 1806: loss 1.7373, time 48.98ms, mfu 0.02%
iter 1807: loss 1.8110, time 41.45ms, mfu 0.02%
iter 1808: loss 1.8539, time 34.03ms, mfu 0.02%
iter 1809: loss 1.8770, time 50.32ms, mfu 0.02%
iter 1810: loss 1.8603, time 55.59ms, mfu 0.02%
iter 1811: loss 1.7364, time 152.14ms, mfu 0.02%
iter 1812: loss 1.7575, time 281.24ms, mfu 0.02%
iter 1813: loss 1.8114, time 147.86ms, mfu 0.02%
iter 1814: loss 1.8269, time 154.07ms, mfu 0.02%
iter 1815: loss 1.8794, time 190.33ms, mfu 0.02%
iter 1816: loss 1.6855, time 291.07ms, mfu 0.01%
iter 1817: loss 1.7748, time 286.72ms, mfu 0.01%
iter 1818: loss 1.8222, time 179.99ms, mfu 0.01%
iter 1819: loss 1.6791, time 114.44ms, mfu 0.01%
iter 1820: loss 1.6907, time 74.30ms, mfu 0.01%
iter 1821: loss 1.7013, time 105.10ms, mfu 0.01%
iter 1822: loss 1.7329, time 88.60ms, mfu 0.01%
iter 1823: loss 1.7331, time 162.61ms, mfu 0.01%
iter 1824: loss 1.6313, time 182.89ms, mfu 0.01%
iter 1825: loss 1.6895, time 78.63ms, mfu 0.01%
iter 1826: loss 1.7253, time 193.18ms, mfu 0.01%
iter 1827: loss 1.7949, time 69.19ms, mfu 0.01%
iter 1828: loss 1.7864, time 62.11ms, mfu 0.01%
iter 1829: loss 1.9065, time 58.27ms, mfu 0.01%
iter 1830: loss 1.7614, time 50.09ms, mfu 0.02%
iter 1831: loss 1.8434, time 58.11ms, mfu 0.02%
iter 1832: loss 1.7082, time 72.41ms, mfu 0.02%
iter 1833: loss 1.8636, time 83.77ms, mfu 0.02%
iter 1834: loss 1.8524, time 66.90ms, mfu 0.02%
iter 1835: loss 1.8769, time 91.35ms, mfu 0.02%
iter 1836: loss 1.7676, time 70.52ms, mfu 0.02%
iter 1837: loss 1.8077, time 56.84ms, mfu 0.02%
iter 1838: loss 1.6216, time 56.42ms, mfu 0.02%
iter 1839: loss 1.7999, time 105.90ms, mfu 0.02%
iter 1840: loss 1.8017, time 97.36ms, mfu 0.02%
iter 1841: loss 1.7604, time 81.73ms, mfu 0.02%
iter 1842: loss 1.7712, time 67.38ms, mfu 0.02%
iter 1843: loss 1.8923, time 39.80ms, mfu 0.02%
iter 1844: loss 1.7598, time 36.00ms, mfu 0.02%
iter 1845: loss 1.8535, time 53.54ms, mfu 0.02%
iter 1846: loss 1.7269, time 56.20ms, mfu 0.02%
iter 1847: loss 1.6867, time 61.08ms, mfu 0.02%
iter 1848: loss 1.7332, time 89.12ms, mfu 0.02%
iter 1849: loss 1.8958, time 220.90ms, mfu 0.02%
iter 1850: loss 1.7283, time 162.16ms, mfu 0.02%
iter 1851: loss 1.7362, time 202.63ms, mfu 0.02%
iter 1852: loss 1.7231, time 118.27ms, mfu 0.02%
iter 1853: loss 1.8270, time 157.84ms, mfu 0.02%
iter 1854: loss 1.6889, time 304.65ms, mfu 0.01%
iter 1855: loss 1.6886, time 134.71ms, mfu 0.01%
iter 1856: loss 1.8231, time 104.99ms, mfu 0.01%
iter 1857: loss 1.8388, time 153.74ms, mfu 0.01%
iter 1858: loss 1.9075, time 166.59ms, mfu 0.01%
iter 1859: loss 1.7361, time 82.73ms, mfu 0.01%
iter 1860: loss 1.6949, time 80.12ms, mfu 0.01%
iter 1861: loss 1.6415, time 139.65ms, mfu 0.01%
iter 1862: loss 1.7298, time 69.62ms, mfu 0.01%
iter 1863: loss 1.7108, time 101.29ms, mfu 0.01%
iter 1864: loss 1.7105, time 109.37ms, mfu 0.01%
iter 1865: loss 1.8216, time 138.28ms, mfu 0.01%
iter 1866: loss 1.7632, time 194.49ms, mfu 0.01%
iter 1867: loss 1.7425, time 112.80ms, mfu 0.01%
iter 1868: loss 1.7308, time 161.89ms, mfu 0.01%
iter 1869: loss 1.8061, time 132.85ms, mfu 0.01%
iter 1870: loss 1.6711, time 65.01ms, mfu 0.01%
iter 1871: loss 1.7664, time 86.60ms, mfu 0.01%
iter 1872: loss 1.7578, time 49.98ms, mfu 0.01%
iter 1873: loss 1.7199, time 63.12ms, mfu 0.01%
iter 1874: loss 1.7120, time 226.70ms, mfu 0.01%
iter 1875: loss 1.6852, time 172.85ms, mfu 0.01%
iter 1876: loss 1.7393, time 171.49ms, mfu 0.01%
iter 1877: loss 1.7477, time 156.74ms, mfu 0.01%
iter 1878: loss 1.6768, time 126.87ms, mfu 0.01%
iter 1879: loss 1.7723, time 101.61ms, mfu 0.01%
iter 1880: loss 1.7548, time 53.67ms, mfu 0.01%
iter 1881: loss 1.7746, time 71.43ms, mfu 0.01%
iter 1882: loss 1.8441, time 78.81ms, mfu 0.01%
iter 1883: loss 1.6335, time 109.26ms, mfu 0.01%
iter 1884: loss 1.7074, time 99.05ms, mfu 0.01%
iter 1885: loss 1.7975, time 68.83ms, mfu 0.01%
iter 1886: loss 1.7024, time 42.39ms, mfu 0.02%
iter 1887: loss 1.8263, time 67.33ms, mfu 0.02%
iter 1888: loss 1.7169, time 75.97ms, mfu 0.02%
iter 1889: loss 1.7219, time 91.65ms, mfu 0.02%
iter 1890: loss 1.6987, time 94.59ms, mfu 0.02%
iter 1891: loss 1.7109, time 63.94ms, mfu 0.02%
iter 1892: loss 1.6612, time 71.44ms, mfu 0.02%
iter 1893: loss 1.7451, time 90.47ms, mfu 0.02%
iter 1894: loss 1.7400, time 67.59ms, mfu 0.02%
iter 1895: loss 1.7499, time 118.90ms, mfu 0.02%
iter 1896: loss 1.7203, time 106.21ms, mfu 0.02%
iter 1897: loss 1.7030, time 90.80ms, mfu 0.02%
iter 1898: loss 1.7733, time 73.29ms, mfu 0.02%
iter 1899: loss 1.7188, time 85.29ms, mfu 0.02%
iter 1900: loss 1.6849, time 77.41ms, mfu 0.02%
iter 1901: loss 1.7666, time 109.77ms, mfu 0.02%
iter 1902: loss 1.8024, time 84.01ms, mfu 0.02%
iter 1903: loss 1.8703, time 72.55ms, mfu 0.02%
iter 1904: loss 1.7309, time 61.76ms, mfu 0.02%
iter 1905: loss 1.7496, time 78.29ms, mfu 0.02%
iter 1906: loss 1.6487, time 108.58ms, mfu 0.02%
iter 1907: loss 1.8226, time 92.28ms, mfu 0.02%
iter 1908: loss 1.7343, time 79.06ms, mfu 0.02%
iter 1909: loss 1.8662, time 297.41ms, mfu 0.01%
iter 1910: loss 1.6221, time 587.14ms, mfu 0.01%
iter 1911: loss 1.7553, time 341.04ms, mfu 0.01%
iter 1912: loss 1.7277, time 292.50ms, mfu 0.01%
iter 1913: loss 1.7665, time 94.31ms, mfu 0.01%
iter 1914: loss 1.7239, time 100.06ms, mfu 0.01%
iter 1915: loss 1.8489, time 339.19ms, mfu 0.01%
iter 1916: loss 1.6891, time 93.80ms, mfu 0.01%
iter 1917: loss 1.7314, time 73.23ms, mfu 0.01%
iter 1918: loss 1.7947, time 90.88ms, mfu 0.01%
iter 1919: loss 1.6894, time 98.19ms, mfu 0.01%
iter 1920: loss 1.7789, time 107.42ms, mfu 0.01%
iter 1921: loss 1.7977, time 72.83ms, mfu 0.01%
iter 1922: loss 1.7670, time 140.81ms, mfu 0.01%
iter 1923: loss 1.7595, time 136.60ms, mfu 0.01%
iter 1924: loss 1.7274, time 71.56ms, mfu 0.01%
iter 1925: loss 1.7422, time 65.89ms, mfu 0.01%
iter 1926: loss 1.8686, time 64.13ms, mfu 0.01%
iter 1927: loss 1.9504, time 62.89ms, mfu 0.01%
iter 1928: loss 1.6605, time 66.81ms, mfu 0.01%
iter 1929: loss 1.7044, time 62.78ms, mfu 0.02%
iter 1930: loss 1.8036, time 63.44ms, mfu 0.02%
iter 1931: loss 1.7936, time 100.11ms, mfu 0.02%
iter 1932: loss 1.8269, time 103.21ms, mfu 0.02%
iter 1933: loss 1.7727, time 44.80ms, mfu 0.02%
iter 1934: loss 1.8015, time 39.92ms, mfu 0.02%
iter 1935: loss 1.7271, time 53.68ms, mfu 0.02%
iter 1936: loss 1.6927, time 41.60ms, mfu 0.02%
iter 1937: loss 1.8060, time 69.21ms, mfu 0.02%
iter 1938: loss 1.7350, time 110.37ms, mfu 0.02%
iter 1939: loss 1.7386, time 52.57ms, mfu 0.02%
iter 1940: loss 1.7062, time 64.26ms, mfu 0.02%
iter 1941: loss 1.6497, time 46.39ms, mfu 0.02%
iter 1942: loss 1.7515, time 42.80ms, mfu 0.02%
iter 1943: loss 1.7952, time 53.15ms, mfu 0.02%
iter 1944: loss 1.8112, time 48.71ms, mfu 0.02%
iter 1945: loss 1.7891, time 52.85ms, mfu 0.02%
iter 1946: loss 1.6995, time 40.19ms, mfu 0.02%
iter 1947: loss 1.7981, time 53.14ms, mfu 0.02%
iter 1948: loss 1.8106, time 72.40ms, mfu 0.02%
iter 1949: loss 1.6782, time 67.55ms, mfu 0.02%
iter 1950: loss 1.7474, time 50.72ms, mfu 0.02%
iter 1951: loss 1.8605, time 60.59ms, mfu 0.02%
iter 1952: loss 1.6390, time 50.95ms, mfu 0.02%
iter 1953: loss 1.8531, time 42.08ms, mfu 0.02%
iter 1954: loss 1.7255, time 47.14ms, mfu 0.02%
iter 1955: loss 1.8938, time 64.67ms, mfu 0.02%
iter 1956: loss 1.7512, time 80.41ms, mfu 0.02%
iter 1957: loss 1.7251, time 66.89ms, mfu 0.02%
iter 1958: loss 1.8246, time 87.02ms, mfu 0.02%
iter 1959: loss 1.7809, time 96.28ms, mfu 0.02%
iter 1960: loss 1.7511, time 149.71ms, mfu 0.02%
iter 1961: loss 1.7355, time 334.85ms, mfu 0.02%
iter 1962: loss 1.8752, time 254.07ms, mfu 0.02%
iter 1963: loss 1.6606, time 244.20ms, mfu 0.02%
iter 1964: loss 1.7129, time 284.03ms, mfu 0.01%
iter 1965: loss 1.8167, time 587.19ms, mfu 0.01%
iter 1966: loss 1.8038, time 567.75ms, mfu 0.01%
iter 1967: loss 1.9572, time 199.57ms, mfu 0.01%
iter 1968: loss 1.6740, time 152.30ms, mfu 0.01%
iter 1969: loss 1.7750, time 74.30ms, mfu 0.01%
iter 1970: loss 1.8327, time 78.22ms, mfu 0.01%
iter 1971: loss 1.7521, time 98.26ms, mfu 0.01%
iter 1972: loss 1.7338, time 134.27ms, mfu 0.01%
iter 1973: loss 1.7306, time 197.12ms, mfu 0.01%
iter 1974: loss 1.6931, time 232.85ms, mfu 0.01%
iter 1975: loss 1.7289, time 77.14ms, mfu 0.01%
iter 1976: loss 1.6929, time 137.65ms, mfu 0.01%
iter 1977: loss 1.8865, time 103.48ms, mfu 0.01%
iter 1978: loss 1.7603, time 147.55ms, mfu 0.01%
iter 1979: loss 1.7862, time 96.08ms, mfu 0.01%
iter 1980: loss 1.7613, time 143.01ms, mfu 0.01%
iter 1981: loss 1.7781, time 107.40ms, mfu 0.01%
iter 1982: loss 1.7722, time 73.53ms, mfu 0.01%
iter 1983: loss 1.7677, time 73.63ms, mfu 0.01%
iter 1984: loss 1.6993, time 70.96ms, mfu 0.01%
iter 1985: loss 1.7417, time 61.77ms, mfu 0.01%
iter 1986: loss 1.6848, time 83.53ms, mfu 0.01%
iter 1987: loss 1.7071, time 87.61ms, mfu 0.01%
iter 1988: loss 1.7093, time 221.67ms, mfu 0.01%
iter 1989: loss 1.6852, time 221.80ms, mfu 0.01%
iter 1990: loss 1.7025, time 167.57ms, mfu 0.01%
iter 1991: loss 1.7723, time 55.29ms, mfu 0.01%
iter 1992: loss 1.6626, time 55.22ms, mfu 0.01%
iter 1993: loss 1.8213, time 49.46ms, mfu 0.02%
iter 1994: loss 1.7564, time 75.13ms, mfu 0.02%
iter 1995: loss 1.7688, time 74.04ms, mfu 0.02%
iter 1996: loss 1.8214, time 63.62ms, mfu 0.02%
iter 1997: loss 1.7120, time 105.69ms, mfu 0.02%
iter 1998: loss 1.8759, time 111.62ms, mfu 0.02%
iter 1999: loss 1.9002, time 102.42ms, mfu 0.01%
step 2000: train loss 1.7648, val loss 1.8857
saving checkpoint to out-shakespeare-char
iter 2000: loss 1.6958, time 1890.64ms, mfu 0.01%
