Buckets:

Mercity
/

Desicion-Model-Custom

Files

xet

Mercity/Desicion-Model-Custom / think-decide /logs /ldr2_multi_train.log

Pranav2748

7 days ago

download

raw

4.38 kB

`torch_dtype` is deprecated! Use `dtype` instead!
{"event": "start", "mode": "multi", "items": 32000, "steps": 564, "questions": 105853, "params": 37819392}
/workspace/think-decide/src/ldr2.py:273: UserWarning: Converting a tensor with requires_grad=True to a scalar may lead to unexpected behavior.
Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:835.)
  rec = dict(step=step, total=total, K=K, loss_final=round(float(losses[K]), 4), grad_norm=round(float(gn), 4),
{"step": 20, "total": 564, "K": 10, "loss_final": 0.4062, "grad_norm": 0.0, "head_o": 0.053, "elapsed": 55.5, "peak_gib": 5.6}
{"step": 40, "total": 564, "K": 3, "loss_final": 0.0036, "grad_norm": 0.0095, "head_o": 0.135, "elapsed": 137.5, "peak_gib": 5.6}
{"step": 60, "total": 564, "K": 7, "loss_final": 0.1633, "grad_norm": 0.0038, "head_o": 0.233, "elapsed": 218.7, "peak_gib": 6.1}
{"step": 80, "total": 564, "K": 4, "loss_final": 0.2268, "grad_norm": 0.001, "head_o": 0.241, "elapsed": 303.8, "peak_gib": 6.2}
{"step": 100, "total": 564, "K": 7, "loss_final": 0.4424, "grad_norm": 0.0016, "head_o": 0.257, "elapsed": 376.5, "peak_gib": 6.2}
{"step": 120, "total": 564, "K": 10, "loss_final": 0.6126, "grad_norm": 0.015, "head_o": 0.258, "elapsed": 450.8, "peak_gib": 6.2}
{"step": 140, "total": 564, "K": 7, "loss_final": 0.0095, "grad_norm": 0.0003, "head_o": 0.192, "elapsed": 523.8, "peak_gib": 6.2}
{"step": 160, "total": 564, "K": 5, "loss_final": 0.2749, "grad_norm": 0.0013, "head_o": 0.2, "elapsed": 595.8, "peak_gib": 6.2}
{"step": 180, "total": 564, "K": 3, "loss_final": 0.2812, "grad_norm": 0.041, "head_o": 0.186, "elapsed": 657.6, "peak_gib": 6.2}
{"step": 200, "total": 564, "K": 2, "loss_final": 0.2873, "grad_norm": 0.02, "head_o": 0.172, "elapsed": 730.7, "peak_gib": 6.2}
{"step": 220, "total": 564, "K": 2, "loss_final": 0.2041, "grad_norm": 0.2804, "head_o": 0.126, "elapsed": 752.0, "peak_gib": 6.2}
{"step": 240, "total": 564, "K": 12, "loss_final": 0.2126, "grad_norm": 0.0013, "head_o": 0.198, "elapsed": 773.8, "peak_gib": 6.2}
{"step": 260, "total": 564, "K": 8, "loss_final": 0.2194, "grad_norm": 0.0005, "head_o": 0.229, "elapsed": 848.8, "peak_gib": 6.2}
{"step": 280, "total": 564, "K": 5, "loss_final": 0.4384, "grad_norm": 0.0336, "head_o": 0.248, "elapsed": 1001.6, "peak_gib": 6.2}
{"step": 300, "total": 564, "K": 5, "loss_final": 0.2419, "grad_norm": 0.0004, "head_o": 0.25, "elapsed": 1038.9, "peak_gib": 6.2}
{"step": 320, "total": 564, "K": 5, "loss_final": 0.2358, "grad_norm": 0.0037, "head_o": 0.25, "elapsed": 1142.6, "peak_gib": 6.2}
{"step": 340, "total": 564, "K": 9, "loss_final": 0.0752, "grad_norm": 0.0, "head_o": 0.244, "elapsed": 1164.4, "peak_gib": 6.2}
{"step": 360, "total": 564, "K": 3, "loss_final": 0.2137, "grad_norm": 0.2572, "head_o": 0.236, "elapsed": 1187.2, "peak_gib": 6.2}
{"step": 380, "total": 564, "K": 10, "loss_final": 0.2663, "grad_norm": 0.0003, "head_o": 0.222, "elapsed": 1205.3, "peak_gib": 6.2}
{"step": 400, "total": 564, "K": 8, "loss_final": 0.339, "grad_norm": 0.0008, "head_o": 0.219, "elapsed": 1227.1, "peak_gib": 6.2}
{"step": 420, "total": 564, "K": 9, "loss_final": 0.2082, "grad_norm": 0.002, "head_o": 0.218, "elapsed": 1247.3, "peak_gib": 6.2}
{"step": 440, "total": 564, "K": 5, "loss_final": 0.0722, "grad_norm": 0.0012, "head_o": 0.227, "elapsed": 1269.0, "peak_gib": 6.2}
{"step": 460, "total": 564, "K": 5, "loss_final": 0.2184, "grad_norm": 0.0008, "head_o": 0.23, "elapsed": 1291.8, "peak_gib": 6.2}
{"step": 480, "total": 564, "K": 5, "loss_final": 0.2879, "grad_norm": 0.0054, "head_o": 0.229, "elapsed": 1312.5, "peak_gib": 6.2}
{"step": 500, "total": 564, "K": 7, "loss_final": 0.3098, "grad_norm": 0.0007, "head_o": 0.224, "elapsed": 1334.4, "peak_gib": 6.2}
{"step": 520, "total": 564, "K": 1, "loss_final": 0.0697, "grad_norm": 0.044, "head_o": 0.222, "elapsed": 1356.3, "peak_gib": 6.2}
{"step": 540, "total": 564, "K": 11, "loss_final": 0.1764, "grad_norm": 0.0001, "head_o": 0.219, "elapsed": 1378.6, "peak_gib": 6.2}
{"step": 560, "total": 564, "K": 1, "loss_final": 0.0784, "grad_norm": 0.0627, "head_o": 0.216, "elapsed": 1397.4, "peak_gib": 6.2}
{"step": 564, "total": 564, "K": 4, "loss_final": 0.1194, "grad_norm": 0.0016, "head_o": 0.216, "elapsed": 1401.4, "peak_gib": 6.2}
{"event": "saved", "elapsed": 1401.7}

Xet Storage Details

Size:: 4.38 kB
Xet hash:: cc3918f5522c1aaa9892a8e12e17ed40e4001e47582614aa1d5ab1ba84277c8e

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.

	`torch_dtype` is deprecated! Use `dtype` instead!
	{"event": "start", "mode": "multi", "items": 32000, "steps": 564, "questions": 105853, "params": 37819392}
	/workspace/think-decide/src/ldr2.py:273: UserWarning: Converting a tensor with requires_grad=True to a scalar may lead to unexpected behavior.
	Consider using tensor.detach() first. (Triggered internally at /pytorch/torch/csrc/autograd/generated/python_variable_methods.cpp:835.)
	rec = dict(step=step, total=total, K=K, loss_final=round(float(losses[K]), 4), grad_norm=round(float(gn), 4),
	{"step": 20, "total": 564, "K": 10, "loss_final": 0.4062, "grad_norm": 0.0, "head_o": 0.053, "elapsed": 55.5, "peak_gib": 5.6}
	{"step": 40, "total": 564, "K": 3, "loss_final": 0.0036, "grad_norm": 0.0095, "head_o": 0.135, "elapsed": 137.5, "peak_gib": 5.6}
	{"step": 60, "total": 564, "K": 7, "loss_final": 0.1633, "grad_norm": 0.0038, "head_o": 0.233, "elapsed": 218.7, "peak_gib": 6.1}
	{"step": 80, "total": 564, "K": 4, "loss_final": 0.2268, "grad_norm": 0.001, "head_o": 0.241, "elapsed": 303.8, "peak_gib": 6.2}
	{"step": 100, "total": 564, "K": 7, "loss_final": 0.4424, "grad_norm": 0.0016, "head_o": 0.257, "elapsed": 376.5, "peak_gib": 6.2}
	{"step": 120, "total": 564, "K": 10, "loss_final": 0.6126, "grad_norm": 0.015, "head_o": 0.258, "elapsed": 450.8, "peak_gib": 6.2}
	{"step": 140, "total": 564, "K": 7, "loss_final": 0.0095, "grad_norm": 0.0003, "head_o": 0.192, "elapsed": 523.8, "peak_gib": 6.2}
	{"step": 160, "total": 564, "K": 5, "loss_final": 0.2749, "grad_norm": 0.0013, "head_o": 0.2, "elapsed": 595.8, "peak_gib": 6.2}
	{"step": 180, "total": 564, "K": 3, "loss_final": 0.2812, "grad_norm": 0.041, "head_o": 0.186, "elapsed": 657.6, "peak_gib": 6.2}
	{"step": 200, "total": 564, "K": 2, "loss_final": 0.2873, "grad_norm": 0.02, "head_o": 0.172, "elapsed": 730.7, "peak_gib": 6.2}
	{"step": 220, "total": 564, "K": 2, "loss_final": 0.2041, "grad_norm": 0.2804, "head_o": 0.126, "elapsed": 752.0, "peak_gib": 6.2}
	{"step": 240, "total": 564, "K": 12, "loss_final": 0.2126, "grad_norm": 0.0013, "head_o": 0.198, "elapsed": 773.8, "peak_gib": 6.2}
	{"step": 260, "total": 564, "K": 8, "loss_final": 0.2194, "grad_norm": 0.0005, "head_o": 0.229, "elapsed": 848.8, "peak_gib": 6.2}
	{"step": 280, "total": 564, "K": 5, "loss_final": 0.4384, "grad_norm": 0.0336, "head_o": 0.248, "elapsed": 1001.6, "peak_gib": 6.2}
	{"step": 300, "total": 564, "K": 5, "loss_final": 0.2419, "grad_norm": 0.0004, "head_o": 0.25, "elapsed": 1038.9, "peak_gib": 6.2}
	{"step": 320, "total": 564, "K": 5, "loss_final": 0.2358, "grad_norm": 0.0037, "head_o": 0.25, "elapsed": 1142.6, "peak_gib": 6.2}
	{"step": 340, "total": 564, "K": 9, "loss_final": 0.0752, "grad_norm": 0.0, "head_o": 0.244, "elapsed": 1164.4, "peak_gib": 6.2}
	{"step": 360, "total": 564, "K": 3, "loss_final": 0.2137, "grad_norm": 0.2572, "head_o": 0.236, "elapsed": 1187.2, "peak_gib": 6.2}
	{"step": 380, "total": 564, "K": 10, "loss_final": 0.2663, "grad_norm": 0.0003, "head_o": 0.222, "elapsed": 1205.3, "peak_gib": 6.2}
	{"step": 400, "total": 564, "K": 8, "loss_final": 0.339, "grad_norm": 0.0008, "head_o": 0.219, "elapsed": 1227.1, "peak_gib": 6.2}
	{"step": 420, "total": 564, "K": 9, "loss_final": 0.2082, "grad_norm": 0.002, "head_o": 0.218, "elapsed": 1247.3, "peak_gib": 6.2}
	{"step": 440, "total": 564, "K": 5, "loss_final": 0.0722, "grad_norm": 0.0012, "head_o": 0.227, "elapsed": 1269.0, "peak_gib": 6.2}
	{"step": 460, "total": 564, "K": 5, "loss_final": 0.2184, "grad_norm": 0.0008, "head_o": 0.23, "elapsed": 1291.8, "peak_gib": 6.2}
	{"step": 480, "total": 564, "K": 5, "loss_final": 0.2879, "grad_norm": 0.0054, "head_o": 0.229, "elapsed": 1312.5, "peak_gib": 6.2}
	{"step": 500, "total": 564, "K": 7, "loss_final": 0.3098, "grad_norm": 0.0007, "head_o": 0.224, "elapsed": 1334.4, "peak_gib": 6.2}
	{"step": 520, "total": 564, "K": 1, "loss_final": 0.0697, "grad_norm": 0.044, "head_o": 0.222, "elapsed": 1356.3, "peak_gib": 6.2}
	{"step": 540, "total": 564, "K": 11, "loss_final": 0.1764, "grad_norm": 0.0001, "head_o": 0.219, "elapsed": 1378.6, "peak_gib": 6.2}
	{"step": 560, "total": 564, "K": 1, "loss_final": 0.0784, "grad_norm": 0.0627, "head_o": 0.216, "elapsed": 1397.4, "peak_gib": 6.2}
	{"step": 564, "total": 564, "K": 4, "loss_final": 0.1194, "grad_norm": 0.0016, "head_o": 0.216, "elapsed": 1401.4, "peak_gib": 6.2}
	{"event": "saved", "elapsed": 1401.7}