Upload train.log with huggingface_hub
Browse files
train.log
CHANGED
|
@@ -1525,3 +1525,45 @@ iter 132400: loss 2.8004, time 440.96ms, mfu 143.48%
|
|
| 1525 |
iter 132500: loss 2.7831, time 439.82ms, mfu 144.69%
|
| 1526 |
iter 132600: loss 2.7491, time 442.04ms, mfu 145.70%
|
| 1527 |
iter 132700: loss 2.7711, time 441.93ms, mfu 146.61%
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1525 |
iter 132500: loss 2.7831, time 439.82ms, mfu 144.69%
|
| 1526 |
iter 132600: loss 2.7491, time 442.04ms, mfu 145.70%
|
| 1527 |
iter 132700: loss 2.7711, time 441.93ms, mfu 146.61%
|
| 1528 |
+
iter 132800: loss 2.7886, time 441.62ms, mfu 147.44%
|
| 1529 |
+
iter 132900: loss 2.7077, time 438.57ms, mfu 148.30%
|
| 1530 |
+
iter 133000: loss 2.7744, time 442.46ms, mfu 148.93%
|
| 1531 |
+
iter 133100: loss 2.8471, time 443.40ms, mfu 149.47%
|
| 1532 |
+
iter 133200: loss 2.7616, time 439.65ms, mfu 150.09%
|
| 1533 |
+
iter 133300: loss 2.8758, time 440.86ms, mfu 150.60%
|
| 1534 |
+
iter 133400: loss 2.7872, time 440.40ms, mfu 151.07%
|
| 1535 |
+
iter 133500: loss 2.8764, time 439.62ms, mfu 151.53%
|
| 1536 |
+
iter 133600: loss 2.7800, time 441.22ms, mfu 151.88%
|
| 1537 |
+
iter 133700: loss 2.8041, time 444.59ms, mfu 152.08%
|
| 1538 |
+
iter 133800: loss 2.8194, time 441.35ms, mfu 152.38%
|
| 1539 |
+
iter 133900: loss 2.7547, time 439.98ms, mfu 152.69%
|
| 1540 |
+
step 134000: train loss 2.7390, val loss 2.7650
|
| 1541 |
+
saving checkpoint to out-wiki-gutenberg-530m-1ep
|
| 1542 |
+
iter 134000: loss 2.7572, time 65663.64ms, mfu 137.53%
|
| 1543 |
+
iter 134100: loss 2.7551, time 440.54ms, mfu 139.31%
|
| 1544 |
+
iter 134200: loss 2.7672, time 439.60ms, mfu 140.94%
|
| 1545 |
+
iter 134300: loss 2.8065, time 442.56ms, mfu 142.31%
|
| 1546 |
+
iter 134400: loss 2.7587, time 441.61ms, mfu 143.57%
|
| 1547 |
+
iter 134500: loss 2.7616, time 441.45ms, mfu 144.71%
|
| 1548 |
+
iter 134600: loss 2.7910, time 435.63ms, mfu 145.94%
|
| 1549 |
+
iter 134700: loss 2.8514, time 440.35ms, mfu 146.89%
|
| 1550 |
+
iter 134800: loss 2.7414, time 441.74ms, mfu 147.69%
|
| 1551 |
+
iter 134900: loss 2.8629, time 440.16ms, mfu 148.46%
|
| 1552 |
+
iter 135000: loss 2.8098, time 439.35ms, mfu 149.19%
|
| 1553 |
+
iter 135100: loss 2.8385, time 443.71ms, mfu 149.69%
|
| 1554 |
+
iter 135200: loss 2.7048, time 440.65ms, mfu 150.25%
|
| 1555 |
+
iter 135300: loss 2.7254, time 444.26ms, mfu 150.63%
|
| 1556 |
+
iter 135400: loss 2.6914, time 441.42ms, mfu 151.06%
|
| 1557 |
+
iter 135500: loss 2.7797, time 441.67ms, mfu 151.45%
|
| 1558 |
+
iter 135600: loss 2.8389, time 442.64ms, mfu 151.76%
|
| 1559 |
+
iter 135700: loss 2.8208, time 441.67ms, mfu 152.08%
|
| 1560 |
+
iter 135800: loss 2.7976, time 441.08ms, mfu 152.38%
|
| 1561 |
+
iter 135900: loss 2.7482, time 440.82ms, mfu 152.66%
|
| 1562 |
+
step 136000: train loss 2.7352, val loss 2.7654
|
| 1563 |
+
saving checkpoint to out-wiki-gutenberg-530m-1ep
|
| 1564 |
+
iter 136000: loss 2.7647, time 65743.26ms, mfu 137.50%
|
| 1565 |
+
iter 136100: loss 2.8031, time 440.62ms, mfu 139.28%
|
| 1566 |
+
iter 136200: loss 2.7676, time 440.96ms, mfu 140.87%
|
| 1567 |
+
iter 136300: loss 2.8472, time 441.35ms, mfu 142.28%
|
| 1568 |
+
iter 136400: loss 2.7656, time 437.28ms, mfu 143.70%
|
| 1569 |
+
iter 136500: loss 2.8012, time 441.28ms, mfu 144.84%
|