From 1f4785715ae0cf917a9b029aa8034637ca9af5cf Mon Sep 17 00:00:00 2001 From: Stella Biderman Date: Sun, 3 Jan 2021 14:24:57 -0500 Subject: [PATCH 1/3] Update requirements.txt --- requirements.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index b1afc98b2..02e07526f 100644 --- a/requirements.txt +++ b/requirements.txt @@ -4,4 +4,3 @@ tqdm>=4.50.0 deepspeed transformers tensorflow==1.15.2 -triton From 0d2ee7e695cff766c07e72e59ab4ddc6043e436f Mon Sep 17 00:00:00 2001 From: Stella Biderman Date: Sun, 3 Jan 2021 14:47:06 -0500 Subject: [PATCH 2/3] turn off validation --- configs/gpt3_small.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/configs/gpt3_small.json b/configs/gpt3_small.json index 69bf7d2fc..5773bfa96 100644 --- a/configs/gpt3_small.json +++ b/configs/gpt3_small.json @@ -23,7 +23,7 @@ "batch_size": 256, "eval_batch_size": 32, "learning_rate": 0.0006, - "validate_every": 100, + "validate_every": 10000000, "generate_every": 500, "generate_length": 256, "seq_len": 1024, @@ -31,4 +31,4 @@ "n_layers": 12, "n_heads": 12, "dim_head": 64 -} \ No newline at end of file +} From 71b4da9b42941266c77d72174a9a50f6dfdabd17 Mon Sep 17 00:00:00 2001 From: Stella Biderman Date: Sun, 3 Jan 2021 14:50:13 -0500 Subject: [PATCH 3/3] Update gpt3_small.json --- configs/gpt3_small.json | 1 - 1 file changed, 1 deletion(-) diff --git a/configs/gpt3_small.json b/configs/gpt3_small.json index 5773bfa96..eec36d65f 100644 --- a/configs/gpt3_small.json +++ b/configs/gpt3_small.json @@ -23,7 +23,6 @@ "batch_size": 256, "eval_batch_size": 32, "learning_rate": 0.0006, - "validate_every": 10000000, "generate_every": 500, "generate_length": 256, "seq_len": 1024,