tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

slightly smaller train set

Browse Source
This commit is contained in:
Wing Lian
2025-04-06 17:08:39 -04:00
parent 98d98ea1dd
commit cf4c84e21d
2 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/e2e/multigpu/test_llama.py
View File

@@ -114,7 +114,7 @@ class TestMultiGPULlama:
"lora_alpha": 16, "lora_alpha": 16,
"lora_dropout": 0.05, "lora_dropout": 0.05,
"lora_target_linear": True, "lora_target_linear": True,
"val_set_size": 0.01, "val_set_size": 0.05,
"special_tokens": { "special_tokens": {
"pad_token": "<|endoftext|>", "pad_token": "<|endoftext|>",
}, },
@@ -122,6 +122,7 @@ class TestMultiGPULlama:
{ {
"path": "tatsu-lab/alpaca", "path": "tatsu-lab/alpaca",
"type": "alpaca", "type": "alpaca",
"split": "train[:20%]",
}, },
], ],
"num_epochs": 1, "num_epochs": 1,

6
tests/e2e/multigpu/test_ray.py
View File

@@ -31,7 +31,7 @@ class TestMultiGPURay:
cfg = DictDefault( cfg = DictDefault(
{ {
"base_model": "HuggingFaceTB/SmolLM2-135M", "base_model": "HuggingFaceTB/SmolLM2-135M",
"sequence_len": 2048, "sequence_len": 1024,
"adapter": "lora", "adapter": "lora",
"lora_r": 8, "lora_r": 8,
"lora_alpha": 16, "lora_alpha": 16,
@@ -94,8 +94,8 @@ class TestMultiGPURay:
"base_model": "HuggingFaceTB/SmolLM2-135M", "base_model": "HuggingFaceTB/SmolLM2-135M",
"sample_packing": True, "sample_packing": True,
"pad_to_sequence_len": True, "pad_to_sequence_len": True,
"sequence_len": 2048, "sequence_len": 1024,
"val_set_size": 0.05, "val_set_size": 0.01,
"special_tokens": { "special_tokens": {
"pad_token": "<|endoftext|>", "pad_token": "<|endoftext|>",
}, },