Hugging Face's logo

CorgiPudding
/
Qwen2.5-Coder-7B-Instruct-Julia

Model card Files
xet
 Community
CorgiPudding commited on
Commit
9a41f11
·
verified ·
1 Parent(s): 414473e

Upload 7 files

Browse files
Files changed (7) hide show
  1. evaluation/eval_2026-01-19-09-54-23/all_results.json +10 -0
  2. evaluation/eval_2026-01-19-09-54-23/generated_predictions.jsonl +0 -0
  3. evaluation/eval_2026-01-19-09-54-23/llamaboard_config.yaml +20 -0
  4. evaluation/eval_2026-01-19-09-54-23/predict_results.json +10 -0
  5. evaluation/eval_2026-01-19-09-54-23/running_log.txt +183 -0
  6. evaluation/eval_2026-01-19-09-54-23/trainer_log.jsonl +108 -0
  7. evaluation/eval_2026-01-19-09-54-23/training_args.yaml +22 -0
evaluation/eval_2026-01-19-09-54-23/all_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu-4": 70.75534080406653,
3
+ "predict_model_preparation_time": 0.0034,
4
+ "predict_rouge-1": 83.16078181608133,
5
+ "predict_rouge-2": 72.07602541589648,
6
+ "predict_rouge-l": 79.7412064926063,
7
+ "predict_runtime": 930.7663,
8
+ "predict_samples_per_second": 4.646,
9
+ "predict_steps_per_second": 0.581
10
+ }
evaluation/eval_2026-01-19-09-54-23/generated_predictions.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
evaluation/eval_2026-01-19-09-54-23/llamaboard_config.yaml ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ eval.batch_size: 2
2
+ eval.cutoff_len: 1024
3
+ eval.dataset:
4
+ - julia_funcBodyV3_test_dataset
5
+ eval.dataset_dir: data
6
+ eval.max_new_tokens: 512
7
+ eval.max_samples: '100000'
8
+ eval.output_dir: eval_2026-01-19-09-54-23
9
+ eval.predict: true
10
+ eval.temperature: 0.95
11
+ eval.top_p: 0.7
12
+ top.booster: auto
13
+ top.checkpoint_path:
14
+ - LLaMA-Factory-main/saves/qwen2.5-coder-7b-instruct/lora/funcBody/sft_v3_39w
15
+ top.finetuning_type: lora
16
+ top.model_name: Qwen2.5-Coder-7B-Instruct
17
+ top.quantization_bit: none
18
+ top.quantization_method: bnb
19
+ top.rope_scaling: none
20
+ top.template: qwen
evaluation/eval_2026-01-19-09-54-23/predict_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu-4": 70.75534080406653,
3
+ "predict_model_preparation_time": 0.0034,
4
+ "predict_rouge-1": 83.16078181608133,
5
+ "predict_rouge-2": 72.07602541589648,
6
+ "predict_rouge-l": 79.7412064926063,
7
+ "predict_runtime": 930.7663,
8
+ "predict_samples_per_second": 4.646,
9
+ "predict_steps_per_second": 0.581
10
+ }
evaluation/eval_2026-01-19-09-54-23/running_log.txt ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file vocab.json
2
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file merges.txt
3
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file tokenizer.json
4
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file added_tokens.json
5
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file special_tokens_map.json
6
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file tokenizer_config.json
7
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file chat_template.jinja
8
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2364 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
9
+ [INFO|2026-01-19 09:56:17] configuration_utils.py:763 >> loading configuration file /home/guoshuai/.cache/modelscope/hub/models/Qwen/Qwen2___5-Coder-7B-Instruct/config.json
10
+ [INFO|2026-01-19 09:56:17] configuration_utils.py:839 >> Model config Qwen2Config {
11
+ "architectures": [
12
+ "Qwen2ForCausalLM"
13
+ ],
14
+ "attention_dropout": 0.0,
15
+ "bos_token_id": 151643,
16
+ "dtype": "bfloat16",
17
+ "eos_token_id": 151645,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 3584,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 18944,
22
+ "layer_types": [
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention"
51
+ ],
52
+ "max_position_embeddings": 32768,
53
+ "max_window_layers": 28,
54
+ "model_type": "qwen2",
55
+ "num_attention_heads": 28,
56
+ "num_hidden_layers": 28,
57
+ "num_key_value_heads": 4,
58
+ "rms_norm_eps": 1e-06,
59
+ "rope_scaling": null,
60
+ "rope_theta": 1000000.0,
61
+ "sliding_window": null,
62
+ "tie_word_embeddings": false,
63
+ "transformers_version": "4.57.1",
64
+ "use_cache": true,
65
+ "use_sliding_window": false,
66
+ "vocab_size": 152064
67
+ }
68
+
69
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file vocab.json
70
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file merges.txt
71
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file tokenizer.json
72
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file added_tokens.json
73
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file special_tokens_map.json
74
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file tokenizer_config.json
75
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2093 >> loading file chat_template.jinja
76
+ [INFO|2026-01-19 09:56:17] tokenization_utils_base.py:2364 >> Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
77
+ [INFO|2026-01-19 09:56:17] logging.py:143 >> Loading dataset ./julia_functionBody_dataset/test_julia_funcsBodyV3_4324.jsonl...
78
+ [INFO|2026-01-19 09:56:22] configuration_utils.py:763 >> loading configuration file /home/guoshuai/.cache/modelscope/hub/models/Qwen/Qwen2___5-Coder-7B-Instruct/config.json
79
+ [INFO|2026-01-19 09:56:22] configuration_utils.py:839 >> Model config Qwen2Config {
80
+ "architectures": [
81
+ "Qwen2ForCausalLM"
82
+ ],
83
+ "attention_dropout": 0.0,
84
+ "bos_token_id": 151643,
85
+ "dtype": "bfloat16",
86
+ "eos_token_id": 151645,
87
+ "hidden_act": "silu",
88
+ "hidden_size": 3584,
89
+ "initializer_range": 0.02,
90
+ "intermediate_size": 18944,
91
+ "layer_types": [
92
+ "full_attention",
93
+ "full_attention",
94
+ "full_attention",
95
+ "full_attention",
96
+ "full_attention",
97
+ "full_attention",
98
+ "full_attention",
99
+ "full_attention",
100
+ "full_attention",
101
+ "full_attention",
102
+ "full_attention",
103
+ "full_attention",
104
+ "full_attention",
105
+ "full_attention",
106
+ "full_attention",
107
+ "full_attention",
108
+ "full_attention",
109
+ "full_attention",
110
+ "full_attention",
111
+ "full_attention",
112
+ "full_attention",
113
+ "full_attention",
114
+ "full_attention",
115
+ "full_attention",
116
+ "full_attention",
117
+ "full_attention",
118
+ "full_attention",
119
+ "full_attention"
120
+ ],
121
+ "max_position_embeddings": 32768,
122
+ "max_window_layers": 28,
123
+ "model_type": "qwen2",
124
+ "num_attention_heads": 28,
125
+ "num_hidden_layers": 28,
126
+ "num_key_value_heads": 4,
127
+ "rms_norm_eps": 1e-06,
128
+ "rope_scaling": null,
129
+ "rope_theta": 1000000.0,
130
+ "sliding_window": null,
131
+ "tie_word_embeddings": false,
132
+ "transformers_version": "4.57.1",
133
+ "use_cache": true,
134
+ "use_sliding_window": false,
135
+ "vocab_size": 152064
136
+ }
137
+
138
+ [WARNING|2026-01-19 09:56:22] logging.py:328 >> `torch_dtype` is deprecated! Use `dtype` instead!
139
+ [INFO|2026-01-19 09:56:22] logging.py:143 >> KV cache is enabled for faster generation.
140
+ [WARNING|2026-01-19 09:56:22] logging.py:328 >> `torch_dtype` is deprecated! Use `dtype` instead!
141
+ [WARNING|2026-01-19 09:56:22] logging.py:328 >> `torch_dtype` is deprecated! Use `dtype` instead!
142
+ [WARNING|2026-01-19 09:56:22] logging.py:328 >> `torch_dtype` is deprecated! Use `dtype` instead!
143
+ [INFO|2026-01-19 09:56:22] modeling_utils.py:1169 >> loading weights file /home/guoshuai/.cache/modelscope/hub/models/Qwen/Qwen2___5-Coder-7B-Instruct/model.safetensors.index.json
144
+ [INFO|2026-01-19 09:56:22] modeling_utils.py:2341 >> Instantiating Qwen2ForCausalLM model under default dtype torch.bfloat16.
145
+ [INFO|2026-01-19 09:56:22] configuration_utils.py:986 >> Generate config GenerationConfig {
146
+ "bos_token_id": 151643,
147
+ "eos_token_id": 151645
148
+ }
149
+
150
+ [WARNING|2026-01-19 09:56:22] logging.py:328 >> `torch_dtype` is deprecated! Use `dtype` instead!
151
+ [WARNING|2026-01-19 09:56:22] logging.py:328 >> `torch_dtype` is deprecated! Use `dtype` instead!
152
+ [WARNING|2026-01-19 09:56:22] logging.py:328 >> `torch_dtype` is deprecated! Use `dtype` instead!
153
+ [WARNING|2026-01-19 09:56:22] logging.py:328 >> `torch_dtype` is deprecated! Use `dtype` instead!
154
+ [INFO|2026-01-19 09:56:42] configuration_utils.py:939 >> loading configuration file /home/guoshuai/.cache/modelscope/hub/models/Qwen/Qwen2___5-Coder-7B-Instruct/generation_config.json
155
+ [INFO|2026-01-19 09:56:42] configuration_utils.py:986 >> Generate config GenerationConfig {
156
+ "bos_token_id": 151643,
157
+ "do_sample": true,
158
+ "eos_token_id": [
159
+ 151645,
160
+ 151643
161
+ ],
162
+ "pad_token_id": 151643,
163
+ "repetition_penalty": 1.1,
164
+ "temperature": 0.7,
165
+ "top_k": 20,
166
+ "top_p": 0.8
167
+ }
168
+
169
+ [INFO|2026-01-19 09:56:42] dynamic_module_utils.py:423 >> Could not locate the custom_generate/generate.py inside /home/guoshuai/.cache/modelscope/hub/models/Qwen/Qwen2___5-Coder-7B-Instruct.
170
+ [INFO|2026-01-19 09:56:42] logging.py:143 >> Using torch SDPA for faster training and inference.
171
+ [INFO|2026-01-19 09:56:43] logging.py:143 >> Merged 1 adapter(s).
172
+ [INFO|2026-01-19 09:56:43] logging.py:143 >> Loaded adapter(s): LLaMA-Factory-main/saves/qwen2.5-coder-7b-instruct/lora/funcBody/sft_v3_39w
173
+ [INFO|2026-01-19 09:56:43] logging.py:143 >> all params: 7,615,616,512
174
+ [WARNING|2026-01-19 09:56:43] trainer.py:906 >> The model is already on multiple devices. Skipping the move to device specified in `args`.
175
+ [WARNING|2026-01-19 09:56:43] logging.py:154 >> Batch generation can be very slow. Consider using `scripts/vllm_infer.py` instead.
176
+ [INFO|2026-01-19 09:56:43] trainer.py:4643 >>
177
+ ***** Running Prediction *****
178
+ [INFO|2026-01-19 09:56:43] trainer.py:4645 >> Num examples = 4324
179
+ [INFO|2026-01-19 09:56:43] trainer.py:4648 >> Batch size = 2
180
+ [WARNING|2026-01-19 09:56:43] trainer.py:906 >> The model is already on multiple devices. Skipping the move to device specified in `args`.
181
+ [WARNING|2026-01-19 09:56:43] trainer.py:906 >> The model is already on multiple devices. Skipping the move to device specified in `args`.
182
+ [WARNING|2026-01-19 09:56:43] trainer.py:906 >> The model is already on multiple devices. Skipping the move to device specified in `args`.
183
+ [INFO|2026-01-19 10:12:14] logging.py:143 >> Saving prediction results to saves/Qwen2.5-Coder-7B-Instruct/lora/eval_2026-01-19-09-54-23/generated_predictions.jsonl
evaluation/eval_2026-01-19-09-54-23/trainer_log.jsonl ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 5, "total_steps": 541, "percentage": 0.92, "elapsed_time": "0:00:05", "remaining_time": "0:09:10"}
2
+ {"current_steps": 10, "total_steps": 541, "percentage": 1.85, "elapsed_time": "0:00:11", "remaining_time": "0:09:48"}
3
+ {"current_steps": 15, "total_steps": 541, "percentage": 2.77, "elapsed_time": "0:00:21", "remaining_time": "0:12:47"}
4
+ {"current_steps": 20, "total_steps": 541, "percentage": 3.7, "elapsed_time": "0:00:26", "remaining_time": "0:11:20"}
5
+ {"current_steps": 25, "total_steps": 541, "percentage": 4.62, "elapsed_time": "0:00:31", "remaining_time": "0:10:51"}
6
+ {"current_steps": 30, "total_steps": 541, "percentage": 5.55, "elapsed_time": "0:00:36", "remaining_time": "0:10:18"}
7
+ {"current_steps": 35, "total_steps": 541, "percentage": 6.47, "elapsed_time": "0:00:48", "remaining_time": "0:11:43"}
8
+ {"current_steps": 40, "total_steps": 541, "percentage": 7.39, "elapsed_time": "0:01:05", "remaining_time": "0:13:41"}
9
+ {"current_steps": 45, "total_steps": 541, "percentage": 8.32, "elapsed_time": "0:01:17", "remaining_time": "0:14:11"}
10
+ {"current_steps": 50, "total_steps": 541, "percentage": 9.24, "elapsed_time": "0:01:20", "remaining_time": "0:13:14"}
11
+ {"current_steps": 55, "total_steps": 541, "percentage": 10.17, "elapsed_time": "0:01:26", "remaining_time": "0:12:44"}
12
+ {"current_steps": 60, "total_steps": 541, "percentage": 11.09, "elapsed_time": "0:01:31", "remaining_time": "0:12:15"}
13
+ {"current_steps": 65, "total_steps": 541, "percentage": 12.01, "elapsed_time": "0:01:34", "remaining_time": "0:11:35"}
14
+ {"current_steps": 70, "total_steps": 541, "percentage": 12.94, "elapsed_time": "0:01:49", "remaining_time": "0:12:18"}
15
+ {"current_steps": 75, "total_steps": 541, "percentage": 13.86, "elapsed_time": "0:02:05", "remaining_time": "0:13:02"}
16
+ {"current_steps": 80, "total_steps": 541, "percentage": 14.79, "elapsed_time": "0:02:24", "remaining_time": "0:13:54"}
17
+ {"current_steps": 85, "total_steps": 541, "percentage": 15.71, "elapsed_time": "0:02:30", "remaining_time": "0:13:27"}
18
+ {"current_steps": 90, "total_steps": 541, "percentage": 16.64, "elapsed_time": "0:02:34", "remaining_time": "0:12:53"}
19
+ {"current_steps": 95, "total_steps": 541, "percentage": 17.56, "elapsed_time": "0:02:37", "remaining_time": "0:12:19"}
20
+ {"current_steps": 100, "total_steps": 541, "percentage": 18.48, "elapsed_time": "0:02:43", "remaining_time": "0:12:02"}
21
+ {"current_steps": 105, "total_steps": 541, "percentage": 19.41, "elapsed_time": "0:02:49", "remaining_time": "0:11:43"}
22
+ {"current_steps": 110, "total_steps": 541, "percentage": 20.33, "elapsed_time": "0:02:54", "remaining_time": "0:11:21"}
23
+ {"current_steps": 115, "total_steps": 541, "percentage": 21.26, "elapsed_time": "0:03:07", "remaining_time": "0:11:35"}
24
+ {"current_steps": 120, "total_steps": 541, "percentage": 22.18, "elapsed_time": "0:03:11", "remaining_time": "0:11:11"}
25
+ {"current_steps": 125, "total_steps": 541, "percentage": 23.11, "elapsed_time": "0:03:31", "remaining_time": "0:11:44"}
26
+ {"current_steps": 130, "total_steps": 541, "percentage": 24.03, "elapsed_time": "0:03:35", "remaining_time": "0:11:22"}
27
+ {"current_steps": 135, "total_steps": 541, "percentage": 24.95, "elapsed_time": "0:03:46", "remaining_time": "0:11:22"}
28
+ {"current_steps": 140, "total_steps": 541, "percentage": 25.88, "elapsed_time": "0:03:53", "remaining_time": "0:11:07"}
29
+ {"current_steps": 145, "total_steps": 541, "percentage": 26.8, "elapsed_time": "0:03:59", "remaining_time": "0:10:53"}
30
+ {"current_steps": 150, "total_steps": 541, "percentage": 27.73, "elapsed_time": "0:04:11", "remaining_time": "0:10:56"}
31
+ {"current_steps": 155, "total_steps": 541, "percentage": 28.65, "elapsed_time": "0:04:17", "remaining_time": "0:10:41"}
32
+ {"current_steps": 160, "total_steps": 541, "percentage": 29.57, "elapsed_time": "0:04:26", "remaining_time": "0:10:33"}
33
+ {"current_steps": 165, "total_steps": 541, "percentage": 30.5, "elapsed_time": "0:04:31", "remaining_time": "0:10:18"}
34
+ {"current_steps": 170, "total_steps": 541, "percentage": 31.42, "elapsed_time": "0:04:34", "remaining_time": "0:09:59"}
35
+ {"current_steps": 175, "total_steps": 541, "percentage": 32.35, "elapsed_time": "0:04:39", "remaining_time": "0:09:43"}
36
+ {"current_steps": 180, "total_steps": 541, "percentage": 33.27, "elapsed_time": "0:04:56", "remaining_time": "0:09:54"}
37
+ {"current_steps": 185, "total_steps": 541, "percentage": 34.2, "elapsed_time": "0:05:08", "remaining_time": "0:09:53"}
38
+ {"current_steps": 190, "total_steps": 541, "percentage": 35.12, "elapsed_time": "0:05:13", "remaining_time": "0:09:39"}
39
+ {"current_steps": 195, "total_steps": 541, "percentage": 36.04, "elapsed_time": "0:05:20", "remaining_time": "0:09:28"}
40
+ {"current_steps": 200, "total_steps": 541, "percentage": 36.97, "elapsed_time": "0:05:31", "remaining_time": "0:09:24"}
41
+ {"current_steps": 205, "total_steps": 541, "percentage": 37.89, "elapsed_time": "0:05:39", "remaining_time": "0:09:15"}
42
+ {"current_steps": 210, "total_steps": 541, "percentage": 38.82, "elapsed_time": "0:05:52", "remaining_time": "0:09:15"}
43
+ {"current_steps": 215, "total_steps": 541, "percentage": 39.74, "elapsed_time": "0:06:00", "remaining_time": "0:09:06"}
44
+ {"current_steps": 220, "total_steps": 541, "percentage": 40.67, "elapsed_time": "0:06:05", "remaining_time": "0:08:53"}
45
+ {"current_steps": 225, "total_steps": 541, "percentage": 41.59, "elapsed_time": "0:06:09", "remaining_time": "0:08:39"}
46
+ {"current_steps": 230, "total_steps": 541, "percentage": 42.51, "elapsed_time": "0:06:13", "remaining_time": "0:08:25"}
47
+ {"current_steps": 235, "total_steps": 541, "percentage": 43.44, "elapsed_time": "0:06:26", "remaining_time": "0:08:23"}
48
+ {"current_steps": 240, "total_steps": 541, "percentage": 44.36, "elapsed_time": "0:06:33", "remaining_time": "0:08:13"}
49
+ {"current_steps": 245, "total_steps": 541, "percentage": 45.29, "elapsed_time": "0:06:36", "remaining_time": "0:07:58"}
50
+ {"current_steps": 250, "total_steps": 541, "percentage": 46.21, "elapsed_time": "0:06:41", "remaining_time": "0:07:47"}
51
+ {"current_steps": 255, "total_steps": 541, "percentage": 47.13, "elapsed_time": "0:06:45", "remaining_time": "0:07:35"}
52
+ {"current_steps": 260, "total_steps": 541, "percentage": 48.06, "elapsed_time": "0:06:49", "remaining_time": "0:07:22"}
53
+ {"current_steps": 265, "total_steps": 541, "percentage": 48.98, "elapsed_time": "0:06:52", "remaining_time": "0:07:09"}
54
+ {"current_steps": 270, "total_steps": 541, "percentage": 49.91, "elapsed_time": "0:07:12", "remaining_time": "0:07:13"}
55
+ {"current_steps": 275, "total_steps": 541, "percentage": 50.83, "elapsed_time": "0:07:17", "remaining_time": "0:07:03"}
56
+ {"current_steps": 280, "total_steps": 541, "percentage": 51.76, "elapsed_time": "0:07:21", "remaining_time": "0:06:51"}
57
+ {"current_steps": 285, "total_steps": 541, "percentage": 52.68, "elapsed_time": "0:07:38", "remaining_time": "0:06:51"}
58
+ {"current_steps": 290, "total_steps": 541, "percentage": 53.6, "elapsed_time": "0:07:43", "remaining_time": "0:06:41"}
59
+ {"current_steps": 295, "total_steps": 541, "percentage": 54.53, "elapsed_time": "0:07:48", "remaining_time": "0:06:30"}
60
+ {"current_steps": 300, "total_steps": 541, "percentage": 55.45, "elapsed_time": "0:07:59", "remaining_time": "0:06:25"}
61
+ {"current_steps": 305, "total_steps": 541, "percentage": 56.38, "elapsed_time": "0:08:06", "remaining_time": "0:06:16"}
62
+ {"current_steps": 310, "total_steps": 541, "percentage": 57.3, "elapsed_time": "0:08:09", "remaining_time": "0:06:04"}
63
+ {"current_steps": 315, "total_steps": 541, "percentage": 58.23, "elapsed_time": "0:08:25", "remaining_time": "0:06:02"}
64
+ {"current_steps": 320, "total_steps": 541, "percentage": 59.15, "elapsed_time": "0:08:29", "remaining_time": "0:05:51"}
65
+ {"current_steps": 325, "total_steps": 541, "percentage": 60.07, "elapsed_time": "0:08:37", "remaining_time": "0:05:43"}
66
+ {"current_steps": 330, "total_steps": 541, "percentage": 61.0, "elapsed_time": "0:09:02", "remaining_time": "0:05:46"}
67
+ {"current_steps": 335, "total_steps": 541, "percentage": 61.92, "elapsed_time": "0:09:07", "remaining_time": "0:05:36"}
68
+ {"current_steps": 340, "total_steps": 541, "percentage": 62.85, "elapsed_time": "0:09:10", "remaining_time": "0:05:25"}
69
+ {"current_steps": 345, "total_steps": 541, "percentage": 63.77, "elapsed_time": "0:09:25", "remaining_time": "0:05:21"}
70
+ {"current_steps": 350, "total_steps": 541, "percentage": 64.7, "elapsed_time": "0:09:41", "remaining_time": "0:05:17"}
71
+ {"current_steps": 355, "total_steps": 541, "percentage": 65.62, "elapsed_time": "0:09:49", "remaining_time": "0:05:08"}
72
+ {"current_steps": 360, "total_steps": 541, "percentage": 66.54, "elapsed_time": "0:09:57", "remaining_time": "0:05:00"}
73
+ {"current_steps": 365, "total_steps": 541, "percentage": 67.47, "elapsed_time": "0:10:06", "remaining_time": "0:04:52"}
74
+ {"current_steps": 370, "total_steps": 541, "percentage": 68.39, "elapsed_time": "0:10:19", "remaining_time": "0:04:46"}
75
+ {"current_steps": 375, "total_steps": 541, "percentage": 69.32, "elapsed_time": "0:10:42", "remaining_time": "0:04:44"}
76
+ {"current_steps": 380, "total_steps": 541, "percentage": 70.24, "elapsed_time": "0:10:50", "remaining_time": "0:04:35"}
77
+ {"current_steps": 385, "total_steps": 541, "percentage": 71.16, "elapsed_time": "0:10:56", "remaining_time": "0:04:25"}
78
+ {"current_steps": 390, "total_steps": 541, "percentage": 72.09, "elapsed_time": "0:11:10", "remaining_time": "0:04:19"}
79
+ {"current_steps": 395, "total_steps": 541, "percentage": 73.01, "elapsed_time": "0:11:17", "remaining_time": "0:04:10"}
80
+ {"current_steps": 400, "total_steps": 541, "percentage": 73.94, "elapsed_time": "0:11:19", "remaining_time": "0:03:59"}
81
+ {"current_steps": 405, "total_steps": 541, "percentage": 74.86, "elapsed_time": "0:11:23", "remaining_time": "0:03:49"}
82
+ {"current_steps": 410, "total_steps": 541, "percentage": 75.79, "elapsed_time": "0:11:36", "remaining_time": "0:03:42"}
83
+ {"current_steps": 415, "total_steps": 541, "percentage": 76.71, "elapsed_time": "0:11:40", "remaining_time": "0:03:32"}
84
+ {"current_steps": 420, "total_steps": 541, "percentage": 77.63, "elapsed_time": "0:11:52", "remaining_time": "0:03:25"}
85
+ {"current_steps": 425, "total_steps": 541, "percentage": 78.56, "elapsed_time": "0:12:00", "remaining_time": "0:03:16"}
86
+ {"current_steps": 430, "total_steps": 541, "percentage": 79.48, "elapsed_time": "0:12:13", "remaining_time": "0:03:09"}
87
+ {"current_steps": 435, "total_steps": 541, "percentage": 80.41, "elapsed_time": "0:12:20", "remaining_time": "0:03:00"}
88
+ {"current_steps": 440, "total_steps": 541, "percentage": 81.33, "elapsed_time": "0:12:25", "remaining_time": "0:02:51"}
89
+ {"current_steps": 445, "total_steps": 541, "percentage": 82.26, "elapsed_time": "0:12:29", "remaining_time": "0:02:41"}
90
+ {"current_steps": 450, "total_steps": 541, "percentage": 83.18, "elapsed_time": "0:12:40", "remaining_time": "0:02:33"}
91
+ {"current_steps": 455, "total_steps": 541, "percentage": 84.1, "elapsed_time": "0:12:49", "remaining_time": "0:02:25"}
92
+ {"current_steps": 460, "total_steps": 541, "percentage": 85.03, "elapsed_time": "0:12:58", "remaining_time": "0:02:17"}
93
+ {"current_steps": 465, "total_steps": 541, "percentage": 85.95, "elapsed_time": "0:13:06", "remaining_time": "0:02:08"}
94
+ {"current_steps": 470, "total_steps": 541, "percentage": 86.88, "elapsed_time": "0:13:10", "remaining_time": "0:01:59"}
95
+ {"current_steps": 475, "total_steps": 541, "percentage": 87.8, "elapsed_time": "0:13:14", "remaining_time": "0:01:50"}
96
+ {"current_steps": 480, "total_steps": 541, "percentage": 88.72, "elapsed_time": "0:13:18", "remaining_time": "0:01:41"}
97
+ {"current_steps": 485, "total_steps": 541, "percentage": 89.65, "elapsed_time": "0:13:29", "remaining_time": "0:01:33"}
98
+ {"current_steps": 490, "total_steps": 541, "percentage": 90.57, "elapsed_time": "0:13:34", "remaining_time": "0:01:24"}
99
+ {"current_steps": 495, "total_steps": 541, "percentage": 91.5, "elapsed_time": "0:13:38", "remaining_time": "0:01:16"}
100
+ {"current_steps": 500, "total_steps": 541, "percentage": 92.42, "elapsed_time": "0:13:42", "remaining_time": "0:01:07"}
101
+ {"current_steps": 505, "total_steps": 541, "percentage": 93.35, "elapsed_time": "0:13:56", "remaining_time": "0:00:59"}
102
+ {"current_steps": 510, "total_steps": 541, "percentage": 94.27, "elapsed_time": "0:14:00", "remaining_time": "0:00:51"}
103
+ {"current_steps": 515, "total_steps": 541, "percentage": 95.19, "elapsed_time": "0:14:05", "remaining_time": "0:00:42"}
104
+ {"current_steps": 520, "total_steps": 541, "percentage": 96.12, "elapsed_time": "0:14:19", "remaining_time": "0:00:34"}
105
+ {"current_steps": 525, "total_steps": 541, "percentage": 97.04, "elapsed_time": "0:14:32", "remaining_time": "0:00:26"}
106
+ {"current_steps": 530, "total_steps": 541, "percentage": 97.97, "elapsed_time": "0:14:58", "remaining_time": "0:00:18"}
107
+ {"current_steps": 535, "total_steps": 541, "percentage": 98.89, "elapsed_time": "0:15:04", "remaining_time": "0:00:10"}
108
+ {"current_steps": 540, "total_steps": 541, "percentage": 99.82, "elapsed_time": "0:15:24", "remaining_time": "0:00:01"}
evaluation/eval_2026-01-19-09-54-23/training_args.yaml ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adapter_name_or_path: LLaMA-Factory-main/saves/qwen2.5-coder-7b-instruct/lora/funcBody/sft_v3_39w
2
+ cutoff_len: 1024
3
+ dataset_dir: data
4
+ ddp_timeout: 180000000
5
+ do_predict: true
6
+ eval_dataset: julia_funcBodyV3_test_dataset
7
+ finetuning_type: lora
8
+ flash_attn: auto
9
+ max_new_tokens: 512
10
+ max_samples: 100000
11
+ model_name_or_path: Qwen/Qwen2.5-Coder-7B-Instruct
12
+ output_dir: saves/Qwen2.5-Coder-7B-Instruct/lora/eval_2026-01-19-09-54-23
13
+ per_device_eval_batch_size: 2
14
+ predict_with_generate: true
15
+ preprocessing_num_workers: 16
16
+ quantization_method: bnb
17
+ report_to: none
18
+ stage: sft
19
+ temperature: 0.95
20
+ template: qwen
21
+ top_p: 0.7
22
+ trust_remote_code: true