morganmcg1
/ minGPT-Fastai_Play_Char.ipynb
Created
August 22, 2020 00:04
Karpathy's minGPT in Fastai
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
morganmcg1
/ BatchNormFP32.py
Created
September 14, 2020 17:49
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| class BatchNormFP32(nn.BatchNorm2d): | |
| def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) | |
| def forward(self, x): return super().forward(x.float()) # CAST BatchNorm input to float | |
| # SWAP OUT REGUALR BN FOR BatchNormFP32 IN YOUR MODEL | |
| def swap_batch_norm(model, layer_type_old, layer_type_new, copy_data=True): | |
| conversion_count = 0 | |
| #TODO : make sure device is correct | |
| for name, module in reversed(model._modules.items()): | |
| if len(list(module.children())) > 0: |
morganmcg1
/ gist:11bef00ba82bfcab9f1fa82cb674bafc
Created
December 18, 2020 20:51
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "cells": [ | |
| { | |
| "cell_type": "markdown", | |
| "metadata": { | |
| "colab_type": "text", | |
| "id": "view-in-github" | |
| }, | |
| "source": [ | |
| "<a href=\"https://colab.research.google.com/github/sheikmohdimran/Experiments_2020/blob/master/NLP/SWT_fastai.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" |
morganmcg1
/ _transformer_tests.ipynb
Created
December 21, 2020 22:37
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
morganmcg1
/ Transformer Tricks to Try
Last active
February 12, 2021 13:02
A bunch of random tricks to try and create the ultimate transformer!
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ARCHITECCTURE | |
| - ADMIN Initialisation | |
| - {{[[TODO]]}} Deeper encoder, shallower decoder | |
| - {{[[TODO]]}} Mish | |
| - DONE? {{[[TODO]]}} Test Impact of embedding tying (would need shared vocab) | |
| - {{[[TODO]]}} Use [[PreLayerNorm]] | |
| - Try #ELU and #[[Shifted RELU]] | |
| - Try [[EDITOR]] transformer: https://jlibovicky.github.io/2020/12/12/MT-Weekly-Editor.html | |
| - Gradient Adaptive Clipping | |
| - Snake Activation: https://twitter.com/EdwardDixon3/status/1360211045491617792?s=20 |
morganmcg1
/ _admin_init.ipynb
Created
February 21, 2021 22:08
Testing out ADMIN with BTE, trained SentencePieceUnigram and PreTrained T5 Tokenizers
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| https://colab.research.google.com/drive/1D6krVG0PPJR2Je9g5eN_2h6JP73_NUXz |
morganmcg1
/ gist:7efefc5dabac971a8198c3e2f6dd15a6
Last active
March 20, 2021 14:57
Colab auto-click, prevent close due to inactivity
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| In case you want to use this google colab to fine-tune your model, you should make sure that | |
| your training doesn't stop due to inactivity. A simple hack to prevent this is to paste the | |
| following code into the console of this tab (right mouse click -> inspect -> Console tab and insert code). | |
| ``` | |
| function ConnectButton(){ | |
| console.log("Connect pushed"); | |
| document.querySelector("#top-toolbar > colab-connect-button").shadowRoot.querySelector("#connect").click() | |
| } | |
| setInterval(ConnectButton,60000); |
morganmcg1
/ sklearn_metrics_logging.ipynb
Created
April 6, 2021 20:08
F1 score using wandb.sklearn.plot_summary_metrics
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
morganmcg1
/ debug-internal.log
Created
April 7, 2021 10:29
wandb run crash - wandb/xlsr-irish/d1isczie
This file has been truncated, but you can view the full file.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 2021-04-06 10:29:46,421 INFO MainThread:30933 [internal.py:wandb_internal():88] W&B internal server running at pid: 30933, started at: 2021-04-06 10:29:46.421160 | |
| 2021-04-06 10:29:46,423 DEBUG SenderThread:30933 [sender.py:send():160] send: header | |
| 2021-04-06 10:29:46,423 DEBUG HandlerThread:30933 [handler.py:handle_request():120] handle_request: check_version | |
| 2021-04-06 10:29:46,423 INFO WriterThread:30933 [datastore.py:open_for_write():77] open: /home/morgan/ml/projects/xlsr_finetune/notebooks/wandb/run-20210406_102945-d1isczie/run-d1isczie.wandb | |
| 2021-04-06 10:29:46,424 DEBUG SenderThread:30933 [sender.py:send():160] send: request | |
| 2021-04-06 10:29:46,424 DEBUG SenderThread:30933 [sender.py:send_request():169] send_request: check_version | |
| 2021-04-06 10:29:46,501 DEBUG SenderThread:30933 [sender.py:send():160] send: run | |
| 2021-04-06 10:29:46,718 INFO SenderThread:30933 [sender.py:_start_run_threads():651] run started: d1isczie with start time 1617701385 | |
| 2021-04-06 10:29:46,718 DEBUG SenderThre |