Text Generation
PEFT
Safetensors
Tamil
English
lora
fact-checking
misinformation-detection
tamil
low-resource-nlp
retrieval-augmented-generation
qwen
conversational
Instructions to use Meclin/TamilRAV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Meclin/TamilRAV with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B") model = PeftModel.from_pretrained(base_model, "Meclin/TamilRAV") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": 650, | |
| "best_metric": 0.6772647500038147, | |
| "best_model_checkpoint": "./tamilrav_checkpoints/checkpoint-650", | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 650, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015396458814472672, | |
| "grad_norm": 0.29363131523132324, | |
| "learning_rate": 1.8e-05, | |
| "loss": 1.4163263320922852, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.030792917628945343, | |
| "grad_norm": 0.265934020280838, | |
| "learning_rate": 3.8e-05, | |
| "loss": 1.188729953765869, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.046189376443418015, | |
| "grad_norm": 0.1696174591779709, | |
| "learning_rate": 5.8e-05, | |
| "loss": 1.0048276901245117, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.061585835257890686, | |
| "grad_norm": 0.1621861755847931, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.939247989654541, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07698229407236336, | |
| "grad_norm": 0.16908901929855347, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.9107258796691895, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09237875288683603, | |
| "grad_norm": 0.16060316562652588, | |
| "learning_rate": 0.000118, | |
| "loss": 0.8661402702331543, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1077752117013087, | |
| "grad_norm": 0.15463921427726746, | |
| "learning_rate": 0.000138, | |
| "loss": 0.8585456848144531, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12317167051578137, | |
| "grad_norm": 0.14651408791542053, | |
| "learning_rate": 0.00015800000000000002, | |
| "loss": 0.8524063110351563, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.13856812933025403, | |
| "grad_norm": 0.1593480259180069, | |
| "learning_rate": 0.00017800000000000002, | |
| "loss": 0.8573471069335937, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15396458814472672, | |
| "grad_norm": 0.14837513864040375, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 0.8089125633239747, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16936104695919937, | |
| "grad_norm": 0.1440625786781311, | |
| "learning_rate": 0.00019998832107530538, | |
| "loss": 0.8235550880432129, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.18475750577367206, | |
| "grad_norm": 0.1411304473876953, | |
| "learning_rate": 0.00019994795298602624, | |
| "loss": 0.8093386650085449, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.20015396458814472, | |
| "grad_norm": 0.1452978402376175, | |
| "learning_rate": 0.0001998787631859678, | |
| "loss": 0.8320710182189941, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2155504234026174, | |
| "grad_norm": 0.13940446078777313, | |
| "learning_rate": 0.00019978077162719857, | |
| "loss": 0.821429443359375, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.23094688221709006, | |
| "grad_norm": 0.14506584405899048, | |
| "learning_rate": 0.00019965400656726942, | |
| "loss": 0.7923899173736573, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.24634334103156275, | |
| "grad_norm": 0.14369885623455048, | |
| "learning_rate": 0.000199498504561065, | |
| "loss": 0.7901590824127197, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2617397998460354, | |
| "grad_norm": 0.14093971252441406, | |
| "learning_rate": 0.00019931431045026255, | |
| "loss": 0.8111134529113769, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.27713625866050806, | |
| "grad_norm": 0.13777726888656616, | |
| "learning_rate": 0.00019910147735040102, | |
| "loss": 0.791386604309082, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2925327174749808, | |
| "grad_norm": 0.1432289332151413, | |
| "learning_rate": 0.00019886006663556426, | |
| "loss": 0.7923940181732178, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.30792917628945343, | |
| "grad_norm": 0.13564977049827576, | |
| "learning_rate": 0.00019859014792068282, | |
| "loss": 0.7843753337860108, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3233256351039261, | |
| "grad_norm": 0.13792838156223297, | |
| "learning_rate": 0.00019829179904145918, | |
| "loss": 0.7822946071624756, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.33872209391839875, | |
| "grad_norm": 0.13952118158340454, | |
| "learning_rate": 0.00019796510603192253, | |
| "loss": 0.7925955772399902, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.35411855273287146, | |
| "grad_norm": 0.13627943396568298, | |
| "learning_rate": 0.00019761016309961948, | |
| "loss": 0.7559749603271484, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3695150115473441, | |
| "grad_norm": 0.13699838519096375, | |
| "learning_rate": 0.00019722707259844756, | |
| "loss": 0.769603681564331, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.3849114703618168, | |
| "grad_norm": 0.13574793934822083, | |
| "learning_rate": 0.0001968159449991397, | |
| "loss": 0.7658140659332275, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.40030792917628943, | |
| "grad_norm": 0.13491615653038025, | |
| "learning_rate": 0.00019637689885740827, | |
| "loss": 0.7487314701080322, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.41570438799076215, | |
| "grad_norm": 0.1336905062198639, | |
| "learning_rate": 0.0001959100607797573, | |
| "loss": 0.7576127052307129, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.4311008468052348, | |
| "grad_norm": 0.12657032907009125, | |
| "learning_rate": 0.0001954155653869735, | |
| "loss": 0.7317625999450683, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.44649730561970746, | |
| "grad_norm": 0.13930626213550568, | |
| "learning_rate": 0.00019489355527530576, | |
| "loss": 0.7514139652252197, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4618937644341801, | |
| "grad_norm": 0.1464177966117859, | |
| "learning_rate": 0.00019434418097534554, | |
| "loss": 0.750247573852539, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.47729022324865283, | |
| "grad_norm": 0.14013901352882385, | |
| "learning_rate": 0.00019376760090861824, | |
| "loss": 0.736499834060669, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.4926866820631255, | |
| "grad_norm": 0.131071999669075, | |
| "learning_rate": 0.0001931639813419, | |
| "loss": 0.7452194690704346, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5080831408775982, | |
| "grad_norm": 0.13927963376045227, | |
| "learning_rate": 0.0001925334963392717, | |
| "loss": 0.7342241764068603, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5234795996920708, | |
| "grad_norm": 0.1341823786497116, | |
| "learning_rate": 0.00019187632771192466, | |
| "loss": 0.7511595726013184, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5388760585065435, | |
| "grad_norm": 0.13563531637191772, | |
| "learning_rate": 0.00019119266496573208, | |
| "loss": 0.7299445629119873, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5542725173210161, | |
| "grad_norm": 0.1313074827194214, | |
| "learning_rate": 0.00019048270524660196, | |
| "loss": 0.7165977001190186, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5696689761354888, | |
| "grad_norm": 0.14486627280712128, | |
| "learning_rate": 0.00018974665328362654, | |
| "loss": 0.710158109664917, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.5850654349499615, | |
| "grad_norm": 0.14865578711032867, | |
| "learning_rate": 0.00018898472133004531, | |
| "loss": 0.7281487941741943, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6004618937644342, | |
| "grad_norm": 0.14025066792964935, | |
| "learning_rate": 0.00018819712910203795, | |
| "loss": 0.7306881904602051, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.6158583525789069, | |
| "grad_norm": 0.1385616809129715, | |
| "learning_rate": 0.00018738410371536545, | |
| "loss": 0.715015983581543, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6312548113933796, | |
| "grad_norm": 0.13913969695568085, | |
| "learning_rate": 0.00018654587961987754, | |
| "loss": 0.6998976230621338, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6466512702078522, | |
| "grad_norm": 0.14493151009082794, | |
| "learning_rate": 0.00018568269853190482, | |
| "loss": 0.7252633094787597, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6620477290223249, | |
| "grad_norm": 0.1407926082611084, | |
| "learning_rate": 0.00018479480936455577, | |
| "loss": 0.705822229385376, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.6774441878367975, | |
| "grad_norm": 0.1485988348722458, | |
| "learning_rate": 0.00018388246815593848, | |
| "loss": 0.7083362579345703, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.6928406466512702, | |
| "grad_norm": 0.13596095144748688, | |
| "learning_rate": 0.00018294593799532752, | |
| "loss": 0.7086032867431641, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7082371054657429, | |
| "grad_norm": 0.1445472687482834, | |
| "learning_rate": 0.00018198548894729765, | |
| "loss": 0.7101798057556152, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7236335642802155, | |
| "grad_norm": 0.13956452906131744, | |
| "learning_rate": 0.0001810013979738462, | |
| "loss": 0.6983530044555664, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.7390300230946882, | |
| "grad_norm": 0.14123016595840454, | |
| "learning_rate": 0.00017999394885452605, | |
| "loss": 0.6674805641174316, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7544264819091608, | |
| "grad_norm": 0.1448190063238144, | |
| "learning_rate": 0.00017896343210461319, | |
| "loss": 0.68931565284729, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.7698229407236336, | |
| "grad_norm": 0.14515918493270874, | |
| "learning_rate": 0.00017791014489133147, | |
| "loss": 0.6919535636901856, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.7852193995381063, | |
| "grad_norm": 0.13914334774017334, | |
| "learning_rate": 0.00017683439094815938, | |
| "loss": 0.6638880729675293, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.8006158583525789, | |
| "grad_norm": 0.14346542954444885, | |
| "learning_rate": 0.00017573648048724327, | |
| "loss": 0.6776976585388184, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.8160123171670516, | |
| "grad_norm": 0.1400802731513977, | |
| "learning_rate": 0.00017461673010994236, | |
| "loss": 0.7085250854492188, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.8314087759815243, | |
| "grad_norm": 0.1518496870994568, | |
| "learning_rate": 0.0001734754627155313, | |
| "loss": 0.6884902000427247, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8468052347959969, | |
| "grad_norm": 0.14645785093307495, | |
| "learning_rate": 0.00017231300740808654, | |
| "loss": 0.7027451992034912, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8622016936104696, | |
| "grad_norm": 0.14037857949733734, | |
| "learning_rate": 0.00017112969940158359, | |
| "loss": 0.6541213035583496, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.8775981524249422, | |
| "grad_norm": 0.14151780307292938, | |
| "learning_rate": 0.0001699258799232323, | |
| "loss": 0.6418449401855468, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.8929946112394149, | |
| "grad_norm": 0.14554472267627716, | |
| "learning_rate": 0.00016870189611507813, | |
| "loss": 0.6883684635162354, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.9083910700538876, | |
| "grad_norm": 0.14308355748653412, | |
| "learning_rate": 0.00016745810093389766, | |
| "loss": 0.6611432552337646, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.9237875288683602, | |
| "grad_norm": 0.153996542096138, | |
| "learning_rate": 0.0001661948530494176, | |
| "loss": 0.6723202705383301, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.939183987682833, | |
| "grad_norm": 0.14034205675125122, | |
| "learning_rate": 0.00016491251674088613, | |
| "loss": 0.6433265686035157, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.9545804464973057, | |
| "grad_norm": 0.15295536816120148, | |
| "learning_rate": 0.00016361146179202666, | |
| "loss": 0.6759867191314697, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.9699769053117783, | |
| "grad_norm": 0.14949378371238708, | |
| "learning_rate": 0.00016229206338440447, | |
| "loss": 0.6557295799255372, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.985373364126251, | |
| "grad_norm": 0.15767240524291992, | |
| "learning_rate": 0.00016095470198923648, | |
| "loss": 0.6578701972961426, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.3094935119152069, | |
| "learning_rate": 0.00015959976325767607, | |
| "loss": 0.656089973449707, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.6772647500038147, | |
| "eval_runtime": 193.0976, | |
| "eval_samples_per_second": 2.978, | |
| "eval_steps_per_second": 0.373, | |
| "step": 650 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1950, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.665508132426875e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |