初始化项目,由ModelHub XC社区提供模型
Model: dreamgen/llama3-8b-assistant-test-run1-sft-e2 Source: Original Platform
This commit is contained in:
@@ -0,0 +1,96 @@
|
||||
{
|
||||
"config_general": {
|
||||
"lighteval_sha": "a98210fd3a2d1e8bface1c32b72ebd5017173a4c",
|
||||
"num_fewshot_seeds": 1,
|
||||
"override_batch_size": -1,
|
||||
"max_samples": null,
|
||||
"job_id": "",
|
||||
"start_time": 7402232.698176069,
|
||||
"end_time": 7403576.701790469,
|
||||
"total_evaluation_time_secondes": "1344.0036143995821",
|
||||
"model_name": "dreamgen/llama3-8b-assistant-test-run1-sft-e2",
|
||||
"model_sha": "2746dba774b2a2ae56ff684225c81b060344a654",
|
||||
"model_dtype": "torch.bfloat16",
|
||||
"model_size": "14.96 GB",
|
||||
"config": null
|
||||
},
|
||||
"results": {
|
||||
"leaderboard|gsm8k|5": {
|
||||
"qem": 0.7005307050796058,
|
||||
"qem_stderr": 0.012616300735519642
|
||||
},
|
||||
"all": {
|
||||
"qem": 0.7005307050796058,
|
||||
"qem_stderr": 0.012616300735519642
|
||||
}
|
||||
},
|
||||
"versions": {
|
||||
"leaderboard|gsm8k|5": 0
|
||||
},
|
||||
"config_tasks": {
|
||||
"leaderboard|gsm8k": {
|
||||
"name": "gsm8k",
|
||||
"prompt_function": "gsm8k",
|
||||
"hf_repo": "gsm8k",
|
||||
"hf_subset": "main",
|
||||
"metric": [
|
||||
"quasi_exact_match_gsm8k"
|
||||
],
|
||||
"hf_avail_splits": [
|
||||
"train",
|
||||
"test"
|
||||
],
|
||||
"evaluation_splits": [
|
||||
"test"
|
||||
],
|
||||
"few_shots_split": null,
|
||||
"few_shots_select": "random_sampling_from_train",
|
||||
"generation_size": 256,
|
||||
"stop_sequence": [
|
||||
"Question:",
|
||||
"Question",
|
||||
":"
|
||||
],
|
||||
"output_regex": null,
|
||||
"num_samples": null,
|
||||
"frozen": false,
|
||||
"suite": [
|
||||
"leaderboard"
|
||||
],
|
||||
"original_num_docs": 1319,
|
||||
"effective_num_docs": 1319,
|
||||
"trust_dataset": true,
|
||||
"must_remove_duplicate_docs": null,
|
||||
"version": 0
|
||||
}
|
||||
},
|
||||
"summary_tasks": {
|
||||
"leaderboard|gsm8k|5": {
|
||||
"hashes": {
|
||||
"hash_examples": "0ed016e24e7512fd",
|
||||
"hash_full_prompts": "f7ab209f6467841e",
|
||||
"hash_input_tokens": "deccfe61ad5cb3d5",
|
||||
"hash_cont_tokens": "fd2549040e624164"
|
||||
},
|
||||
"truncated": 1319,
|
||||
"non_truncated": 0,
|
||||
"padded": 1074,
|
||||
"non_padded": 245,
|
||||
"effective_few_shots": 5.0,
|
||||
"num_truncated_few_shots": 0
|
||||
}
|
||||
},
|
||||
"summary_general": {
|
||||
"hashes": {
|
||||
"hash_examples": "bc71463e88551d0e",
|
||||
"hash_full_prompts": "c29e3bdf1c4887c9",
|
||||
"hash_input_tokens": "e975d4ecbb7368e5",
|
||||
"hash_cont_tokens": "84e6a099183a178a"
|
||||
},
|
||||
"truncated": 1319,
|
||||
"non_truncated": 0,
|
||||
"padded": 1074,
|
||||
"non_padded": 245,
|
||||
"num_truncated_few_shots": 0
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user