deb101 commited on
Commit
6151342
·
verified ·
1 Parent(s): fe29bfb

Trained L2R token ranking model on MIMIC-IV

Browse files
training_l2r_log_2025-05-29_19-25-52.log ADDED
@@ -0,0 +1,599 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-05-29 19:25:52,028 - INFO - 📝 Logging initialized. Log file created at: ../tmp/logs/training_l2r_log_2025-05-29_19-25-52.log - [learning2rank.py:264:setup_logging]
2
+ 2025-05-29 19:25:52,028 - INFO - ================================================================================ - [learning2rank.py:108:log_section]
3
+ 2025-05-29 19:25:52,028 - INFO - = 📌 INITIALIZING TRAINING ENVIRONMENT = - [learning2rank.py:109:log_section]
4
+ 2025-05-29 19:25:52,028 - INFO - ================================================================================ - [learning2rank.py:112:log_section]
5
+ 2025-05-29 19:25:52,028 - INFO - 🚀 Setting up data paths and environment variables... - [learning2rank.py:3841:main]
6
+ 2025-05-29 19:25:52,028 - INFO - 🛠️ Command-line Arguments: - [learning2rank.py:280:print_args]
7
+ 2025-05-29 19:25:52,029 - INFO -
8
+ 🔹 output_dir: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r
9
+ 🔹 source_url: XURLs.MIMIC4_DEMO
10
+ 🔹 data: mimic4_icd10_full
11
+ 🔹 data_l2r_fname_prefix: mimic4_icd10
12
+ 🔹 logfile: training_l2r_log
13
+ 🔹 base_dir: ../tmp/MIMIC4_DEMO
14
+ 🔹 l2r_boot_dir: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b
15
+ 🔹 hub_model_id: deb101/mistral-7b-instruct-v0.3-mimic4-adapt
16
+ 🔹 model_name: mistralai/Mistral-7B-Instruct-v0.3
17
+ 🔹 max_length: 512
18
+ 🔹 do_fresh_training: True
19
+ 🔹 load_from_checkpoint: False
20
+ 🔹 task: l2r
21
+ 🔹 num_train_epochs: 4
22
+ 🔹 metric_for_best_model: ndcg@25
23
+ 🔹 learning_rate: 0.0001
24
+ 🔹 warmup_steps: 0
25
+ 🔹 generate_report: False
26
+ 🔹 logfile_path: ../tmp/logs/training_l2r_log_2025-05-29_19-25-52.log
27
+ 🔹 source: /home/ubuntu/.xcube/data/mimic4_demo - [learning2rank.py:281:print_args]
28
+ 2025-05-29 19:25:52,029 - INFO - ➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖ - [learning2rank.py:282:print_args]
29
+ 2025-05-29 19:25:52,029 - INFO - 📁 Using L2R boot directory: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b - [learning2rank.py:3855:main]
30
+ 2025-05-29 19:25:52,029 - INFO - 📂 Using output directory: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:3857:main]
31
+ 2025-05-29 19:25:52,029 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
32
+ 2025-05-29 19:25:52,029 - INFO - + ✨ LOADING DATASETS + - [learning2rank.py:109:log_section]
33
+ 2025-05-29 19:25:52,029 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
34
+ 2025-05-29 19:25:52,029 - INFO - 📊 Loading main dataset and L2R dataset... - [learning2rank.py:3860:main]
35
+ 2025-05-29 19:25:52,029 - INFO - 📂 Loading main data from: /home/ubuntu/.xcube/data/mimic4_demo/mimic4_icd10_full.csv - [learning2rank.py:310:get_data]
36
+ 2025-05-29 19:26:00,147 - INFO - ✅ Successfully loaded main data: 122279 rows - [learning2rank.py:323:get_data]
37
+ 2025-05-29 19:26:00,147 - INFO - 📂 Loading L2R data from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok_rank_per_lbl.ft - [learning2rank.py:329:get_data]
38
+ 2025-05-29 19:26:00,147 - INFO - 📂 Loading L2R tokens from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_tok.ft - [learning2rank.py:332:get_data]
39
+ 2025-05-29 19:26:00,147 - INFO - 📂 Loading L2R labels from: ../tmp/MIMIC4_DEMO/mimic4_l2rboot_mistral7b/mimic4_icd10_lbl.ft - [learning2rank.py:335:get_data]
40
+ 2025-05-29 19:26:01,853 - INFO - ✅ Successfully loaded L2R data: 260243456 rows - [learning2rank.py:342:get_data]
41
+ 2025-05-29 19:26:01,853 - INFO - ✅ Successfully loaded L2R tokens: 32768 tokens - [learning2rank.py:343:get_data]
42
+ 2025-05-29 19:26:01,853 - INFO - ✅ Successfully loaded L2R labels: 7942 rows - [learning2rank.py:344:get_data]
43
+ 2025-05-29 19:26:01,853 - INFO - 🔄 Total data loaded: 122279 main rows, 260243456 L2R rows - [learning2rank.py:351:get_data]
44
+ 2025-05-29 19:26:01,853 - INFO - ✨ Successfully loaded both datasets: - [learning2rank.py:375:load_datasets]
45
+ 2025-05-29 19:26:01,853 - INFO - - 📄 Main dataset: 122279 records - [learning2rank.py:376:load_datasets]
46
+ 2025-05-29 19:26:01,853 - INFO - - 📄 L2R dataset: 260243456 records - [learning2rank.py:377:load_datasets]
47
+ 2025-05-29 19:26:01,853 - INFO - - 🔤 Tokens: 32768 items - [learning2rank.py:378:load_datasets]
48
+ 2025-05-29 19:26:01,853 - INFO - - 🏷️ Labels: 7942 items - [learning2rank.py:379:load_datasets]
49
+ 2025-05-29 19:26:01,860 - INFO - ✅ Data loading completed successfully - [learning2rank.py:387:load_datasets]
50
+ 2025-05-29 19:26:03,128 - INFO - ⏳ Starting quantization of ranks for DataFrame with 260243456 rows. Containing 32768 unique tokens & 7942 unique labels - [learning2rank.py:506:quantize_l2r_data]
51
+ 2025-05-29 19:26:03,129 - INFO - 🔄 Quantizing those 32768 unique token ranks into 101 quantization levels for each label - [learning2rank.py:531:quantize_l2r_data]
52
+ 2025-05-29 19:26:49,291 - INFO - ✅ Completed quantization: Produced tensor of shape torch.Size([7942, 32768, 4]) with 101 quantization levels per label - [learning2rank.py:585:quantize_l2r_data]
53
+ 2025-05-29 19:26:49,320 - WARNING - Label 1295: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
54
+ 2025-05-29 19:26:49,326 - WARNING - Label 4049: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
55
+ 2025-05-29 19:26:49,330 - WARNING - Label 3517: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
56
+ 2025-05-29 19:26:49,334 - WARNING - Label 4308: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
57
+ 2025-05-29 19:26:49,337 - WARNING - Label 519: Only 1 tokens with top relevance score (need 50) - [learning2rank.py:701:test_scored_tokens]
58
+ 2025-05-29 19:26:49,365 - INFO - ******************************************************************************** - [learning2rank.py:108:log_section]
59
+ 2025-05-29 19:26:49,365 - INFO - * 🌟 STARTING LEARNING TO RANK MODEL TRAINING * - [learning2rank.py:109:log_section]
60
+ 2025-05-29 19:26:49,365 - INFO - ******************************************************************************** - [learning2rank.py:112:log_section]
61
+ 2025-05-29 19:26:49,366 - INFO - 🔐 Loaded authentication token from environment - [learning2rank.py:3889:main]
62
+ 2025-05-29 19:26:49,366 - INFO - 🏷️ Hub Model ID for this Learning to Rank task: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:3893:main]
63
+ 2025-05-29 19:26:49,366 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:108:log_section]
64
+ 2025-05-29 19:26:49,366 - INFO - - 📋 MODEL EXISTENCE CHECK - - [learning2rank.py:109:log_section]
65
+ 2025-05-29 19:26:49,366 - INFO - -------------------------------------------------------------------------------- - [learning2rank.py:112:log_section]
66
+ 2025-05-29 19:26:49,366 - INFO - 🔍 Checking model existence locally and on Hugging Face Hub... - [learning2rank.py:407:check_model_existence]
67
+ 2025-05-29 19:26:49,366 - INFO - ❌ Model not found locally at: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:414:check_model_existence]
68
+ 2025-05-29 19:26:49,481 - INFO - ✅ Model exists on Hugging Face Hub with ID: deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r - [learning2rank.py:426:check_model_existence]
69
+ 2025-05-29 19:26:49,481 - INFO - 📁 Model exists either locally or on Hub - [learning2rank.py:452:check_model_existence]
70
+ 2025-05-29 19:26:49,481 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
71
+ 2025-05-29 19:26:49,481 - INFO - + ✨ STARTING FRESH TRAINING + - [learning2rank.py:109:log_section]
72
+ 2025-05-29 19:26:49,481 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
73
+ 2025-05-29 19:26:49,481 - INFO - 🔄 Starting fresh training (either forced or model not found)... - [learning2rank.py:3906:main]
74
+ 2025-05-29 19:26:49,496 - WARNING - Note: Environment variable`HF_TOKEN` is set and is the current active token independently from the token you've just configured. - [_login.py:415:_login]
75
+ 2025-05-29 19:26:49,496 - INFO - 🔑 Successfully authenticated with Hugging Face Hub - [learning2rank.py:288:authenticate_hf]
76
+ 2025-05-29 19:26:49,496 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
77
+ 2025-05-29 19:26:49,496 - INFO - + ✨ LOADING BASE MODEL + - [learning2rank.py:109:log_section]
78
+ 2025-05-29 19:26:49,496 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
79
+ 2025-05-29 19:26:49,496 - INFO - 📥 Loading pretrained model and tokenizer... - [learning2rank.py:3948:main]
80
+ 2025-05-29 19:26:49,496 - INFO - 🚀 Starting model and tokenizer loading process... - [learning2rank.py:916:load_base_model_and_tokenizer]
81
+ 2025-05-29 19:26:49,497 - INFO - 📊 Quantization config: BitsAndBytesConfig {
82
+ "_load_in_4bit": true,
83
+ "_load_in_8bit": false,
84
+ "bnb_4bit_compute_dtype": "bfloat16",
85
+ "bnb_4bit_quant_storage": "uint8",
86
+ "bnb_4bit_quant_type": "nf4",
87
+ "bnb_4bit_use_double_quant": true,
88
+ "llm_int8_enable_fp32_cpu_offload": false,
89
+ "llm_int8_has_fp16_weight": false,
90
+ "llm_int8_skip_modules": null,
91
+ "llm_int8_threshold": 6.0,
92
+ "load_in_4bit": true,
93
+ "load_in_8bit": false,
94
+ "quant_method": "bitsandbytes"
95
+ }
96
+ - [learning2rank.py:925:load_base_model_and_tokenizer]
97
+ 2025-05-29 19:26:49,497 - INFO - 🔤 Loading tokenizer for model: mistralai/Mistral-7B-Instruct-v0.3... - [learning2rank.py:929:load_base_model_and_tokenizer]
98
+ 2025-05-29 19:26:50,177 - INFO - 📝 Setting pad token to eos token... - [learning2rank.py:933:load_base_model_and_tokenizer]
99
+ 2025-05-29 19:26:50,177 - INFO - 🧠 Loading base model with quantization... - [learning2rank.py:941:load_base_model_and_tokenizer]
100
+ 2025-05-29 19:26:50,740 - INFO - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). - [modeling.py:991:get_balanced_memory]
101
+ 2025-05-29 19:26:56,190 - INFO - 🔧 Setting up default LoRA configuration... - [learning2rank.py:964:load_base_model_and_tokenizer]
102
+ 2025-05-29 19:26:56,190 - INFO - 🔍 LoRA config: r=16, alpha=32, targets={'o_proj', 'q_proj', 'k_proj', 'v_proj'}, dropout=0.05 - [learning2rank.py:987:load_base_model_and_tokenizer]
103
+ 2025-05-29 19:26:56,190 - INFO - 🧩 Applying LoRA adapters to model... - [learning2rank.py:994:load_base_model_and_tokenizer]
104
+ 2025-05-29 19:26:56,374 - INFO - ✅ Model and tokenizer successfully loaded! - [learning2rank.py:1001:load_base_model_and_tokenizer]
105
+ 2025-05-29 19:26:56,374 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
106
+ 2025-05-29 19:26:56,374 - INFO - + ✨ DATA PREPROCESSING + - [learning2rank.py:109:log_section]
107
+ 2025-05-29 19:26:56,374 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
108
+ 2025-05-29 19:26:56,374 - INFO - 🔄 Loading and preprocessing training data... - [learning2rank.py:3956:main]
109
+ 2025-05-29 19:26:57,442 - INFO - 🔍 Verifying uniqueness of token IDs per label in scored_tokens... - [learning2rank.py:1279:preprocess_data]
110
+ 2025-05-29 19:26:58,264 - INFO - ✅ All labels have unique token IDs in scored_tokens. - [learning2rank.py:1291:preprocess_data]
111
+ 2025-05-29 19:26:58,264 - INFO - 🚀 Building a 2D lookup table for efficient token-to-relevance mapping across all labels! 🚀 - [learning2rank.py:1294:preprocess_data]
112
+ 2025-05-29 19:26:58,264 - INFO - 🔢 Total labels = 7942 - [learning2rank.py:1297:preprocess_data]
113
+ 2025-05-29 19:26:58,264 - INFO - 🔍 Precomputing token indices and corresponding relevance_values for each label... - [learning2rank.py:1298:preprocess_data]
114
+ 2025-05-29 19:26:58,492 - INFO - 📊 Lookup table dimensions: 32768 vocabulary size × 7942 labels - [learning2rank.py:1305:preprocess_data]
115
+ 2025-05-29 19:26:58,492 - INFO - ⚡ This approach eliminates token comparison broadcasting and provides O(1) lookup time for relevance scores! - [learning2rank.py:1308:preprocess_data]
116
+ 2025-05-29 19:26:58,492 - INFO - 🧮 Processing relevance calculations vectorized for maximum speed 🔥 - [learning2rank.py:1311:preprocess_data]
117
+ 2025-05-29 19:26:58,657 - INFO - 🔍 Verifying token mappings with 10 samples... - [learning2rank.py:1344:verify_token_mappings]
118
+ 2025-05-29 19:26:58,838 - INFO - ✅ Token mappings verification completed successfully! 🎉 - [learning2rank.py:1435:verify_token_mappings]
119
+ 2025-05-29 19:26:58,842 - INFO - 🔄 Processing dataset with map... - [learning2rank.py:1499:preprocess_data]
120
+ 2025-05-29 19:26:59,159 - INFO - ✅ Dataset built in 0h 0m 0.32s - [learning2rank.py:1522:preprocess_data]
121
+ 2025-05-29 19:26:59,171 - INFO - The size of Training set: 173 🏋️ (Training Data) - [learning2rank.py:1553:preprocess_data]
122
+ 2025-05-29 19:26:59,172 - INFO - The size of Evaluation set: 35 🔍 (Test Data) - [learning2rank.py:1554:preprocess_data]
123
+ 2025-05-29 19:26:59,172 - INFO - 🚀 Created HuggingFace Dataset with 208 samples, 7942 labels - [learning2rank.py:1562:preprocess_data]
124
+ 2025-05-29 19:26:59,172 - INFO - 🏷️ Number of unique ICD-10 codes: 7942 - [learning2rank.py:3969:main]
125
+ 2025-05-29 19:26:59,173 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
126
+ 2025-05-29 19:26:59,173 - INFO - + ✨ MODEL INITIALIZATION + - [learning2rank.py:109:log_section]
127
+ 2025-05-29 19:26:59,173 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
128
+ 2025-05-29 19:26:59,173 - INFO - 🧠 Initializing custom L2R model for outputting per-token relevance scores per ICD-10 codes. - [learning2rank.py:3972:main]
129
+ 2025-05-29 19:27:00,707 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
130
+ 2025-05-29 19:27:00,707 - INFO - + ✨ TRAINING PREPARATION + - [learning2rank.py:109:log_section]
131
+ 2025-05-29 19:27:00,707 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
132
+ 2025-05-29 19:27:00,707 - INFO - ⚙️ Preparing training components and optimizers... - [learning2rank.py:3979:main]
133
+ 2025-05-29 19:27:00,739 - INFO - 🖥️ Device: NVIDIA GH200 480GB - [learning2rank.py:2007:log_training_configuration]
134
+ 2025-05-29 19:27:00,739 - INFO - 🔋 CUDA Available: True - [learning2rank.py:2010:log_training_configuration]
135
+ 2025-05-29 19:27:00,739 - INFO - 💾 CUDA Device Count: 1 - [learning2rank.py:2011:log_training_configuration]
136
+ 2025-05-29 19:27:00,740 - INFO -
137
+ 📋 Training Configuration 📋
138
+ +----------+-----------------------------+--------------------------------------------------+
139
+ | 🌟 Emoji | 🏷️ Parameter | 📊 Value |
140
+ +----------+-----------------------------+--------------------------------------------------+
141
+ | 📁 | Output Directory | ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r |
142
+ | 🔁 | Training Epochs | 4 |
143
+ | 🏋️ | Train Batch Size | 1 |
144
+ | 🔍 | Eval Batch Size | 1 |
145
+ | 📊 | Gradient Accumulation Steps | 4 |
146
+ | 🚀 | Learning Rate | 0.0001 |
147
+ | 🌅 | Warmup Steps | 0 |
148
+ | 💾 | Save Strategy | epoch |
149
+ | 💾 | Save Total Limit | 10 |
150
+ | 📊 | Evaluation Strategy | epoch |
151
+ | 🎯 | Best Model Metric | ndcg@25 |
152
+ | 📝 | Logging Strategy | steps (every 10 steps) |
153
+ | 🌐 | Push to Hub | True |
154
+ | 🌐 | Hub Model ID | deb101/mistral-7b-instruct-v0.3-mimic4-adapt-l2r |
155
+ | 🔢 | Steps per Epoch | 43 |
156
+ | 🔢 | Total Training Steps | 172 |
157
+ | 🔢 | Evaluation Steps | 35 |
158
+ | 📊 | Training Dataset Size | 173 samples 🏋️ |
159
+ | 📊 | Evaluation Dataset Size | 35 samples 🔍 |
160
+ +----------+-----------------------------+--------------------------------------------------+ - [learning2rank.py:1999:log_training_args]
161
+ 2025-05-29 19:27:00,740 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
162
+ 2025-05-29 19:27:00,740 - INFO - + ✨ MODEL TRAINING + - [learning2rank.py:109:log_section]
163
+ 2025-05-29 19:27:00,740 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
164
+ 2025-05-29 19:27:00,740 - INFO - 🏋️ Starting model training process... - [learning2rank.py:3999:main]
165
+ 2025-05-29 19:27:00,740 - INFO - 🏁 Preparing Custom Trainer 🛠️ - [learning2rank.py:3200:train_model]
166
+ 2025-05-29 19:27:00,784 - INFO - We are registering the tokenizer mistralai/Mistral-7B-Instruct-v0.3 in Custom Trainer - [learning2rank.py:2639:__init__]
167
+ 2025-05-29 19:27:00,784 - INFO - 🏋️ Commencing Model Training 💪 - [learning2rank.py:3241:train_model]
168
+ 2025-05-29 19:27:01,050 - INFO - 🚀 Starting Training... - [learning2rank.py:2389:on_train_begin]
169
+ 2025-05-29 19:27:20,294 - INFO -
170
+ 🚂 Training Metrics (Step 10) 🚂
171
+ +---------------+--------------+
172
+ | Metric | Value |
173
+ +===============+==============+
174
+ | loss | -4.58268e+16 |
175
+ +---------------+--------------+
176
+ | grad_norm | nan |
177
+ +---------------+--------------+
178
+ | learning_rate | 0.0001 |
179
+ +---------------+--------------+
180
+ | epoch | 0.231214 |
181
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
182
+ 2025-05-29 19:27:34,347 - INFO -
183
+ 🚂 Training Metrics (Step 20) 🚂
184
+ +---------------+--------------+
185
+ | Metric | Value |
186
+ +===============+==============+
187
+ | loss | -4.34403e+17 |
188
+ +---------------+--------------+
189
+ | grad_norm | nan |
190
+ +---------------+--------------+
191
+ | learning_rate | 0.0001 |
192
+ +---------------+--------------+
193
+ | epoch | 0.462428 |
194
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
195
+ 2025-05-29 19:27:48,535 - INFO -
196
+ 🚂 Training Metrics (Step 30) 🚂
197
+ +---------------+--------------+
198
+ | Metric | Value |
199
+ +===============+==============+
200
+ | loss | -6.33341e+16 |
201
+ +---------------+--------------+
202
+ | grad_norm | nan |
203
+ +---------------+--------------+
204
+ | learning_rate | 0.0001 |
205
+ +---------------+--------------+
206
+ | epoch | 0.693642 |
207
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
208
+ 2025-05-29 19:28:02,663 - INFO -
209
+ 🚂 Training Metrics (Step 40) ���
210
+ +---------------+--------------+
211
+ | Metric | Value |
212
+ +===============+==============+
213
+ | loss | -6.34723e+18 |
214
+ +---------------+--------------+
215
+ | grad_norm | nan |
216
+ +---------------+--------------+
217
+ | learning_rate | 0.0001 |
218
+ +---------------+--------------+
219
+ | epoch | 0.924855 |
220
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
221
+ 2025-05-29 19:28:07,197 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2755:evaluate]
222
+ 2025-05-29 19:31:21,756 - WARNING - No valid samples found for metric 'precision@25'. - [learning2rank.py:2859:evaluate]
223
+ 2025-05-29 19:31:21,757 - INFO -
224
+ 🔍 Evaluation Metrics 🔍
225
+ +-------------------+--------------+
226
+ | Metric | Value |
227
+ +===================+==============+
228
+ | eval_loss | -1.17021e+17 |
229
+ +-------------------+--------------+
230
+ | eval_ndcg | 0.955488 |
231
+ +-------------------+--------------+
232
+ | eval_ndcg@25 | 0.18984 |
233
+ +-------------------+--------------+
234
+ | eval_precision@25 | 0 |
235
+ +-------------------+--------------+ - [learning2rank.py:2326:on_evaluate]
236
+ 2025-05-29 19:31:23,021 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-44 - [learning2rank.py:2879:_save]
237
+ 2025-05-29 19:31:23,022 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-44 - [learning2rank.py:2884:_save]
238
+ 2025-05-29 19:31:23,023 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-44:
239
+ +---------+-------------------+------------+
240
+ | Index | Saved File | Size |
241
+ +=========+===================+============+
242
+ | 1 | training_args.bin | 0.01 MB |
243
+ +---------+-------------------+------------+
244
+ | 2 | model.safetensors | 4122.74 MB |
245
+ +---------+-------------------+------------+
246
+ | 3 | config.json | 0.00 MB |
247
+ +---------+-------------------+------------+ - [learning2rank.py:2901:_save]
248
+ 2025-05-29 19:31:36,370 - INFO -
249
+ 🚂 Training Metrics (Step 50) 🚂
250
+ +---------------+--------------+
251
+ | Metric | Value |
252
+ +===============+==============+
253
+ | loss | -4.29741e+18 |
254
+ +---------------+--------------+
255
+ | grad_norm | nan |
256
+ +---------------+--------------+
257
+ | learning_rate | 0.0001 |
258
+ +---------------+--------------+
259
+ | epoch | 1.13873 |
260
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
261
+ 2025-05-29 19:31:50,557 - INFO -
262
+ 🚂 Training Metrics (Step 60) 🚂
263
+ +---------------+--------------+
264
+ | Metric | Value |
265
+ +===============+==============+
266
+ | loss | -1.10586e+17 |
267
+ +---------------+--------------+
268
+ | grad_norm | nan |
269
+ +---------------+--------------+
270
+ | learning_rate | 9.9e-05 |
271
+ +---------------+--------------+
272
+ | epoch | 1.36994 |
273
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
274
+ 2025-05-29 19:32:04,594 - INFO -
275
+ 🚂 Training Metrics (Step 70) 🚂
276
+ +---------------+--------------+
277
+ | Metric | Value |
278
+ +===============+==============+
279
+ | loss | -6.65756e+18 |
280
+ +---------------+--------------+
281
+ | grad_norm | 2.41222e+18 |
282
+ +---------------+--------------+
283
+ | learning_rate | 9.4e-05 |
284
+ +---------------+--------------+
285
+ | epoch | 1.60116 |
286
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
287
+ 2025-05-29 19:32:18,534 - INFO -
288
+ 🚂 Training Metrics (Step 80) 🚂
289
+ +---------------+--------------+
290
+ | Metric | Value |
291
+ +===============+==============+
292
+ | loss | -9.52556e+16 |
293
+ +---------------+--------------+
294
+ | grad_norm | 1.31876e+18 |
295
+ +---------------+--------------+
296
+ | learning_rate | 8.8e-05 |
297
+ +---------------+--------------+
298
+ | epoch | 1.83237 |
299
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
300
+ 2025-05-29 19:32:28,622 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2755:evaluate]
301
+ 2025-05-29 19:35:41,610 - INFO -
302
+ 🔍 Evaluation Metrics 🔍
303
+ +-------------------+--------------+
304
+ | Metric | Value |
305
+ +===================+==============+
306
+ | eval_loss | -3.19605e+17 |
307
+ +-------------------+--------------+
308
+ | eval_ndcg | 0.956218 |
309
+ +-------------------+--------------+
310
+ | eval_ndcg@25 | 0.644859 |
311
+ +-------------------+--------------+
312
+ | eval_precision@25 | 0.524571 |
313
+ +-------------------+--------------+ - [learning2rank.py:2326:on_evaluate]
314
+ 2025-05-29 19:35:42,773 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-88 - [learning2rank.py:2879:_save]
315
+ 2025-05-29 19:35:42,774 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-88 - [learning2rank.py:2884:_save]
316
+ 2025-05-29 19:35:42,775 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-88:
317
+ +---------+-------------------+------------+
318
+ | Index | Saved File | Size |
319
+ +=========+===================+============+
320
+ | 1 | training_args.bin | 0.01 MB |
321
+ +---------+-------------------+------------+
322
+ | 2 | model.safetensors | 4122.74 MB |
323
+ +---------+-------------------+------------+
324
+ | 3 | config.json | 0.00 MB |
325
+ +---------+-------------------+------------+ - [learning2rank.py:2901:_save]
326
+ 2025-05-29 19:35:50,541 - INFO -
327
+ 🚂 Training Metrics (Step 90) 🚂
328
+ +---------------+--------------+
329
+ | Metric | Value |
330
+ +===============+==============+
331
+ | loss | -7.78904e+17 |
332
+ +---------------+--------------+
333
+ | grad_norm | 4.04588e+17 |
334
+ +---------------+--------------+
335
+ | learning_rate | 8.3e-05 |
336
+ +---------------+--------------+
337
+ | epoch | 2.04624 |
338
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
339
+ 2025-05-29 19:36:04,506 - INFO -
340
+ 🚂 Training Metrics (Step 100) 🚂
341
+ +---------------+--------------+
342
+ | Metric | Value |
343
+ +===============+==============+
344
+ | loss | -2.16708e+17 |
345
+ +---------------+--------------+
346
+ | grad_norm | 6.69977e+17 |
347
+ +---------------+--------------+
348
+ | learning_rate | 7.7e-05 |
349
+ +---------------+--------------+
350
+ | epoch | 2.27746 |
351
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
352
+ 2025-05-29 19:36:18,486 - INFO -
353
+ 🚂 Training Metrics (Step 110) 🚂
354
+ +---------------+-------------+
355
+ | Metric | Value |
356
+ +===============+=============+
357
+ | loss | -3.3602e+18 |
358
+ +---------------+-------------+
359
+ | grad_norm | nan |
360
+ +---------------+-------------+
361
+ | learning_rate | 7.3e-05 |
362
+ +---------------+-------------+
363
+ | epoch | 2.50867 |
364
+ +---------------+-------------+ - [learning2rank.py:2307:on_log]
365
+ 2025-05-29 19:36:32,497 - INFO -
366
+ 🚂 Training Metrics (Step 120) 🚂
367
+ +---------------+--------------+
368
+ | Metric | Value |
369
+ +===============+==============+
370
+ | loss | -4.15132e+17 |
371
+ +---------------+--------------+
372
+ | grad_norm | 7.31787e+17 |
373
+ +---------------+--------------+
374
+ | learning_rate | 6.7e-05 |
375
+ +---------------+--------------+
376
+ | epoch | 2.73988 |
377
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
378
+ 2025-05-29 19:36:46,461 - INFO -
379
+ 🚂 Training Metrics (Step 130) 🚂
380
+ +---------------+--------------+
381
+ | Metric | Value |
382
+ +===============+==============+
383
+ | loss | -1.23755e+18 |
384
+ +---------------+--------------+
385
+ | grad_norm | 2.11757e+17 |
386
+ +---------------+--------------+
387
+ | learning_rate | 6.2e-05 |
388
+ +---------------+--------------+
389
+ | epoch | 2.9711 |
390
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
391
+ 2025-05-29 19:36:48,212 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2755:evaluate]
392
+ 2025-05-29 19:40:00,995 - INFO -
393
+ 🔍 Evaluation Metrics 🔍
394
+ +-------------------+--------------+
395
+ | Metric | Value |
396
+ +===================+==============+
397
+ | eval_loss | -4.05479e+17 |
398
+ +-------------------+--------------+
399
+ | eval_ndcg | 0.956806 |
400
+ +-------------------+--------------+
401
+ | eval_ndcg@25 | 0.793177 |
402
+ +-------------------+--------------+
403
+ | eval_precision@25 | 0.890286 |
404
+ +-------------------+--------------+ - [learning2rank.py:2326:on_evaluate]
405
+ 2025-05-29 19:40:02,153 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-132 - [learning2rank.py:2879:_save]
406
+ 2025-05-29 19:40:02,154 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-132 - [learning2rank.py:2884:_save]
407
+ 2025-05-29 19:40:02,155 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-132:
408
+ +---------+-------------------+------------+
409
+ | Index | Saved File | Size |
410
+ +=========+===================+============+
411
+ | 1 | training_args.bin | 0.01 MB |
412
+ +---------+-------------------+------------+
413
+ | 2 | model.safetensors | 4122.74 MB |
414
+ +---------+-------------------+------------+
415
+ | 3 | config.json | 0.00 MB |
416
+ +---------+-------------------+------------+ - [learning2rank.py:2901:_save]
417
+ 2025-05-29 19:40:18,266 - INFO -
418
+ 🚂 Training Metrics (Step 140) 🚂
419
+ +---------------+--------------+
420
+ | Metric | Value |
421
+ +===============+==============+
422
+ | loss | -9.65112e+18 |
423
+ +---------------+--------------+
424
+ | grad_norm | 1.7024e+17 |
425
+ +---------------+--------------+
426
+ | learning_rate | 5.7e-05 |
427
+ +---------------+--------------+
428
+ | epoch | 3.18497 |
429
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
430
+ 2025-05-29 19:40:32,114 - INFO -
431
+ 🚂 Training Metrics (Step 150) 🚂
432
+ +---------------+--------------+
433
+ | Metric | Value |
434
+ +===============+==============+
435
+ | loss | -6.81527e+18 |
436
+ +---------------+--------------+
437
+ | grad_norm | 1.33906e+17 |
438
+ +---------------+--------------+
439
+ | learning_rate | 5.2e-05 |
440
+ +---------------+--------------+
441
+ | epoch | 3.41619 |
442
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
443
+ 2025-05-29 19:40:45,965 - INFO -
444
+ 🚂 Training Metrics (Step 160) 🚂
445
+ +---------------+--------------+
446
+ | Metric | Value |
447
+ +===============+==============+
448
+ | loss | -4.90954e+17 |
449
+ +---------------+--------------+
450
+ | grad_norm | 2.87998e+17 |
451
+ +---------------+--------------+
452
+ | learning_rate | 4.6e-05 |
453
+ +---------------+--------------+
454
+ | epoch | 3.6474 |
455
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
456
+ 2025-05-29 19:40:59,736 - INFO -
457
+ 🚂 Training Metrics (Step 170) 🚂
458
+ +---------------+--------------+
459
+ | Metric | Value |
460
+ +===============+==============+
461
+ | loss | -3.49743e+17 |
462
+ +---------------+--------------+
463
+ | grad_norm | 2.0459e+17 |
464
+ +---------------+--------------+
465
+ | learning_rate | 4e-05 |
466
+ +---------------+--------------+
467
+ | epoch | 3.87861 |
468
+ +---------------+--------------+ - [learning2rank.py:2307:on_log]
469
+ 2025-05-29 19:41:03,699 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2879:_save]
470
+ 2025-05-29 19:41:03,701 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2884:_save]
471
+ 2025-05-29 19:41:03,701 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172:
472
+ +---------+-------------------+------------+
473
+ | Index | Saved File | Size |
474
+ +=========+===================+============+
475
+ | 1 | training_args.bin | 0.01 MB |
476
+ +---------+-------------------+------------+
477
+ | 2 | model.safetensors | 4122.74 MB |
478
+ +---------+-------------------+------------+
479
+ | 3 | config.json | 0.00 MB |
480
+ +---------+-------------------+------------+ - [learning2rank.py:2901:_save]
481
+ 2025-05-29 19:41:03,908 - INFO - Removing 'token_type_ids' from eval_dataset as they are not needed. - [learning2rank.py:2755:evaluate]
482
+ 2025-05-29 19:44:16,555 - INFO -
483
+ 🔍 Evaluation Metrics 🔍
484
+ +-------------------+-------------+
485
+ | Metric | Value |
486
+ +===================+=============+
487
+ | eval_loss | -4.1649e+17 |
488
+ +-------------------+-------------+
489
+ | eval_ndcg | 0.956866 |
490
+ +-------------------+-------------+
491
+ | eval_ndcg@25 | 0.873974 |
492
+ +-------------------+-------------+
493
+ | eval_precision@25 | 0.930286 |
494
+ +-------------------+-------------+ - [learning2rank.py:2326:on_evaluate]
495
+ 2025-05-29 19:44:18,478 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2879:_save]
496
+ 2025-05-29 19:44:18,479 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2884:_save]
497
+ 2025-05-29 19:44:18,480 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172:
498
+ +---------+--------------------+------------+
499
+ | Index | Saved File | Size |
500
+ +=========+====================+============+
501
+ | 1 | training_args.bin | 0.01 MB |
502
+ +---------+--------------------+------------+
503
+ | 2 | optimizer.pt | 352.39 MB |
504
+ +---------+--------------------+------------+
505
+ | 3 | model.safetensors | 4122.74 MB |
506
+ +---------+--------------------+------------+
507
+ | 4 | scaler.pt | 0.00 MB |
508
+ +---------+--------------------+------------+
509
+ | 5 | config.json | 0.00 MB |
510
+ +---------+--------------------+------------+
511
+ | 6 | scheduler.pt | 0.00 MB |
512
+ +---------+--------------------+------------+
513
+ | 7 | trainer_state.json | 0.00 MB |
514
+ +---------+--------------------+------------+
515
+ | 8 | rng_state.pth | 0.01 MB |
516
+ +---------+--------------------+------------+ - [learning2rank.py:2901:_save]
517
+ 2025-05-29 19:44:18,765 - INFO - 📂 Loading best model from ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172 - [learning2rank.py:2957:_load_best_model]
518
+ 2025-05-29 19:44:18,765 - INFO - 🖥️ Model is on device: cuda:0 - [learning2rank.py:2967:_load_best_model]
519
+ 2025-05-29 19:44:18,821 - INFO - 🔑 Key order comparison:
520
+ +---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
521
+ | Index | Saved state_dict Keys | Model state_dict Keys |
522
+ +=========+========================================================================+=============================================================================================+
523
+ | 1 | base_model.base_model.model.lm_head.weight | base_model.base_model.model.model.embed_tokens.weight |
524
+ +---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
525
+ | 2 | base_model.base_model.model.model.embed_tokens.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight |
526
+ +---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
527
+ | 3 | base_model.base_model.model.model.layers.0.input_layernorm.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.absmax |
528
+ +---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
529
+ | 4 | base_model.base_model.model.model.layers.0.mlp.down_proj.weight | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.quant_map |
530
+ +---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+
531
+ | 5 | base_model.base_model.model.model.layers.0.mlp.down_proj.weight.absmax | base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight.nested_absmax |
532
+ +---------+------------------------------------------------------------------------+---------------------------------------------------------------------------------------------+ - [learning2rank.py:2991:_load_best_model]
533
+ 2025-05-29 19:44:19,629 - INFO - ✅ Loaded best model weights from ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/checkpoint-172/model.safetensors - [learning2rank.py:3008:_load_best_model]
534
+ 2025-05-29 19:44:19,686 - INFO - ✔️ Weight for base_model.base_model.model.model.embed_tokens.weight matches between saved and loaded state_dict - [learning2rank.py:3020:_load_best_model]
535
+ 2025-05-29 19:44:19,708 - INFO - ✔️ Weight for base_model.base_model.model.model.layers.0.self_attn.q_proj.base_layer.weight matches between saved and loaded state_dict - [learning2rank.py:3020:_load_best_model]
536
+ 2025-05-29 19:44:19,725 - INFO -
537
+ 🚂 Training Metrics (Step 172) 🚂
538
+ +--------------------------+--------------+
539
+ | Metric | Value |
540
+ +==========================+==============+
541
+ | train_runtime | 1038.68 |
542
+ +--------------------------+--------------+
543
+ | train_samples_per_second | 0.666 |
544
+ +--------------------------+--------------+
545
+ | train_steps_per_second | 0.166 |
546
+ +--------------------------+--------------+
547
+ | total_flos | 0 |
548
+ +--------------------------+--------------+
549
+ | train_loss | -2.40817e+18 |
550
+ +--------------------------+--------------+
551
+ | epoch | 3.92485 |
552
+ +--------------------------+--------------+ - [learning2rank.py:2307:on_log]
553
+ 2025-05-29 19:44:19,726 - INFO - ✨ Training Completed! ✨ - [learning2rank.py:2456:on_train_end]
554
+ 2025-05-29 19:44:19,800 - INFO - 📊 Training loss plot saved as '../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/train_loss_plot.png' - [learning2rank.py:2559:on_train_end]
555
+ 2025-05-29 19:44:19,858 - INFO - 📊 Evaluation loss plot saved as '../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/eval_loss_plot.png' - [learning2rank.py:2573:on_train_end]
556
+ 2025-05-29 19:44:19,918 - INFO - 📊 Evaluation metric plot saved as '../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r/eval_ndcg@25_plot.png' - [learning2rank.py:2594:on_train_end]
557
+ 2025-05-29 19:44:19,919 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:108:log_section]
558
+ 2025-05-29 19:44:19,919 - INFO - + ✨ MODEL SAVING + - [learning2rank.py:109:log_section]
559
+ 2025-05-29 19:44:19,919 - INFO - ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ - [learning2rank.py:112:log_section]
560
+ 2025-05-29 19:44:19,919 - INFO - 💾 Saving trained model and pushing to Hugging Face Hub... - [learning2rank.py:4014:main]
561
+ 2025-05-29 19:44:19,919 - INFO - 📁 Creating/using output directory: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:3275:save_and_push]
562
+ 2025-05-29 19:44:21,100 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:2879:_save]
563
+ 2025-05-29 19:44:21,102 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:2884:_save]
564
+ 2025-05-29 19:44:21,103 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r:
565
+ +---------+-----------------------+------------+
566
+ | Index | Saved File | Size |
567
+ +=========+=======================+============+
568
+ | 1 | eval_loss_plot.png | 0.03 MB |
569
+ +---------+-----------------------+------------+
570
+ | 2 | training_args.bin | 0.01 MB |
571
+ +---------+-----------------------+------------+
572
+ | 3 | model.safetensors | 4122.74 MB |
573
+ +---------+-----------------------+------------+
574
+ | 4 | eval_ndcg@25_plot.png | 0.03 MB |
575
+ +---------+-----------------------+------------+
576
+ | 5 | config.json | 0.00 MB |
577
+ +---------+-----------------------+------------+
578
+ | 6 | train_loss_plot.png | 0.04 MB |
579
+ +---------+-----------------------+------------+ - [learning2rank.py:2901:_save]
580
+ 2025-05-29 19:44:24,684 - INFO - 💾 Model weights saved in safetensors format: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:2879:_save]
581
+ 2025-05-29 19:44:24,685 - INFO - ⚙️ Config saved in checkpoint: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:2884:_save]
582
+ 2025-05-29 19:44:24,686 - INFO - 📋 Saved files in ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r:
583
+ +---------+-----------------------+------------+
584
+ | Index | Saved File | Size |
585
+ +=========+=======================+============+
586
+ | 1 | eval_loss_plot.png | 0.03 MB |
587
+ +---------+-----------------------+------------+
588
+ | 2 | training_args.bin | 0.01 MB |
589
+ +---------+-----------------------+------------+
590
+ | 3 | model.safetensors | 4122.74 MB |
591
+ +---------+-----------------------+------------+
592
+ | 4 | eval_ndcg@25_plot.png | 0.03 MB |
593
+ +---------+-----------------------+------------+
594
+ | 5 | config.json | 0.00 MB |
595
+ +---------+-----------------------+------------+
596
+ | 6 | train_loss_plot.png | 0.04 MB |
597
+ +---------+-----------------------+------------+ - [learning2rank.py:2901:_save]
598
+ 2025-05-29 19:45:41,784 - INFO - 💾 Model saved to: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:3279:save_and_push]
599
+ 2025-05-29 19:45:41,814 - INFO - 🖌️ Tokenizer saved to: ../tmp/MIMIC4_DEMO/mistral7b_mimic4_l2r - [learning2rank.py:3283:save_and_push]