Introduction of Pretraining-SCPWiki-032025-12B-Instruct
Model Details of Pretraining-SCPWiki-032025-12B-Instruct
See axolotl config
axolotl version:
0.8.0.dev0
base_model:mistralai/Mistral-Nemo-Base-2407# optionally might have model_type or tokenizer_typemodel_type:AutoModelForCausalLMtokenizer_type:AutoTokenizer# Automatically upload checkpoint and final model to HFhub_model_id:AiAF/Pretraining-SCPWiki-032025-12B-Instructload_in_8bit:falseload_in_4bit:falsestrict:falsedatasets:-path:AiAF/Pretraining-SCPWiki-032025-7B-Instruct-pretraining.jsonltype:completiondataset_prepared_path:last_run_preparedval_set_size:0.1output_dir:./outputs/out/Pretraining-SCPWiki-032025-12B-V1sequence_len:8192sample_packing:truepad_to_sequence_len:trueeval_sample_packing:falsewandb_project:"LLM-Pretraining"wandb_entity:wandb_watch:"all"wandb_name:"Pretraining-SCPWiki-032025-12B-V1"wandb_log_model:"false"gradient_accumulation_steps:4micro_batch_size:2num_epochs:1optimizer:adamw_bnb_8bitlr_scheduler:cosinelearning_rate:0.000005train_on_inputs:falsegroup_by_length:falsebf16:autofp16:tf32:falsegradient_checkpointing:trueearly_stopping_patience:resume_from_checkpoint:local_rank:logging_steps:1xformers_attention:flash_attention:trueloss_watchdog_threshold:5.0loss_watchdog_patience:3save_total_limit:30warmup_steps:10evals_per_epoch:20eval_table_size:eval_max_new_tokens:128saves_per_epoch:20debug:deepspeed:weight_decay:0.0fsdp:fsdp_config:special_tokens:eos_token:"<|im_end|>"pad_token:"<pad>"bos_token:"<s>"unk_token:"<unk>"tokens:-"<|im_start|>"
Pretraining-SCPWiki-032025-12B-Instruct
This model is a fine-tuned version of
mistralai/Mistral-Nemo-Base-2407
on the AiAF/Pretraining-SCPWiki-032025-7B-Instruct-pretraining.jsonl dataset.
It achieves the following results on the evaluation set:
Loss: 1.5467
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 5e-06
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 1.0
Training results
Training Loss
Epoch
Step
Validation Loss
3.1576
0.0018
1
3.5143
1.4459
0.0511
29
1.6213
1.4502
0.1022
58
1.6003
1.5545
0.1534
87
1.5870
1.3624
0.2045
116
1.5779
1.3053
0.2556
145
1.5691
1.5688
0.3067
174
1.5635
1.7144
0.3579
203
1.5594
1.5199
0.4090
232
1.5550
1.2483
0.4601
261
1.5516
1.4053
0.5112
290
1.5493
1.4238
0.5624
319
1.5486
1.4939
0.6135
348
1.5477
1.4072
0.6646
377
1.5472
1.6039
0.7157
406
1.5469
1.3127
0.7669
435
1.5468
1.4754
0.8180
464
1.5466
1.5992
0.8691
493
1.5467
1.421
0.9202
522
1.5467
1.2666
0.9714
551
1.5467
Framework versions
Transformers 4.49.0
Pytorch 2.5.1+cu124
Datasets 3.2.0
Tokenizers 0.21.0
Runs of AiAF Pretraining-SCPWiki-032025-12B-Instruct on huggingface.co
19
Total runs
0
24-hour runs
7
3-day runs
4
7-day runs
9
30-day runs
More Information About Pretraining-SCPWiki-032025-12B-Instruct huggingface.co Model
More Pretraining-SCPWiki-032025-12B-Instruct license Visit here:
Pretraining-SCPWiki-032025-12B-Instruct huggingface.co is an AI model on huggingface.co that provides Pretraining-SCPWiki-032025-12B-Instruct's model effect (), which can be used instantly with this AiAF Pretraining-SCPWiki-032025-12B-Instruct model. huggingface.co supports a free trial of the Pretraining-SCPWiki-032025-12B-Instruct model, and also provides paid use of the Pretraining-SCPWiki-032025-12B-Instruct. Support call Pretraining-SCPWiki-032025-12B-Instruct model through api, including Node.js, Python, http.
Pretraining-SCPWiki-032025-12B-Instruct huggingface.co is an online trial and call api platform, which integrates Pretraining-SCPWiki-032025-12B-Instruct's modeling effects, including api services, and provides a free online trial of Pretraining-SCPWiki-032025-12B-Instruct, you can try Pretraining-SCPWiki-032025-12B-Instruct online for free by clicking the link below.
AiAF Pretraining-SCPWiki-032025-12B-Instruct online free url in huggingface.co:
Pretraining-SCPWiki-032025-12B-Instruct is an open source model from GitHub that offers a free installation service, and any user can find Pretraining-SCPWiki-032025-12B-Instruct on GitHub to install. At the same time, huggingface.co provides the effect of Pretraining-SCPWiki-032025-12B-Instruct install, users can directly use Pretraining-SCPWiki-032025-12B-Instruct installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Pretraining-SCPWiki-032025-12B-Instruct install url in huggingface.co: