Instructions to use Colin1337X/broken-tutu-24b-unslop-v2.0-lora-limaRP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Colin1337X/broken-tutu-24b-unslop-v2.0-lora-limaRP with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Colin1337X/broken-tutu-24b-unslop-v2.0-lora-limaRP", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download checkpoint-6500/trainer_state.json from Colin1337X/broken-tutu-24b-unslop-v2.0-lora-limaRP: direct link, hf CLI and curl.
- Browser
- Download file 12.2 kB
-
https://huggingface.co/Colin1337X/broken-tutu-24b-unslop-v2.0-lora-limaRP/resolve/main/checkpoint-6500/trainer_state.json
- Command line
-
hf download hf://Colin1337X/broken-tutu-24b-unslop-v2.0-lora-limaRP/checkpoint-6500/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/Colin1337X/broken-tutu-24b-unslop-v2.0-lora-limaRP/resolve/main/checkpoint-6500/trainer_state.json
12.2 kB
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02256734834524918, | |
| "eval_steps": 500, | |
| "global_step": 6500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00034718997454229514, | |
| "grad_norm": 0.8856930732727051, | |
| "learning_rate": 0.00019999994169931, | |
| "loss": 2.4069, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0006943799490845903, | |
| "grad_norm": 0.8890424966812134, | |
| "learning_rate": 0.0001999997644357777, | |
| "loss": 2.3882, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0010415699236268853, | |
| "grad_norm": 0.8619076013565063, | |
| "learning_rate": 0.00019999946820366553, | |
| "loss": 2.4208, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.0013887598981691806, | |
| "grad_norm": 0.8981874585151672, | |
| "learning_rate": 0.00019999905300332595, | |
| "loss": 2.3859, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.0017359498727114757, | |
| "grad_norm": 1.1088451147079468, | |
| "learning_rate": 0.0001999985188352529, | |
| "loss": 2.4031, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.0020831398472537705, | |
| "grad_norm": 0.8845599889755249, | |
| "learning_rate": 0.00019999786570008187, | |
| "loss": 2.3765, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.002430329821796066, | |
| "grad_norm": 1.1892898082733154, | |
| "learning_rate": 0.0001999970935985899, | |
| "loss": 2.4083, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.002777519796338361, | |
| "grad_norm": 1.2907609939575195, | |
| "learning_rate": 0.00019999620253169554, | |
| "loss": 2.4262, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.003124709770880656, | |
| "grad_norm": 1.511342167854309, | |
| "learning_rate": 0.00019999519250045886, | |
| "loss": 2.4077, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.0034718997454229513, | |
| "grad_norm": 1.2708256244659424, | |
| "learning_rate": 0.00019999406350608152, | |
| "loss": 2.4238, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.003819089719965246, | |
| "grad_norm": 1.380018949508667, | |
| "learning_rate": 0.00019999281554990668, | |
| "loss": 2.4429, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.004166279694507541, | |
| "grad_norm": 1.5074928998947144, | |
| "learning_rate": 0.000199991448633419, | |
| "loss": 2.4212, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.004513469669049836, | |
| "grad_norm": 1.20973801612854, | |
| "learning_rate": 0.00019998996275824465, | |
| "loss": 2.4092, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.004860659643592132, | |
| "grad_norm": 1.4226404428482056, | |
| "learning_rate": 0.0001999883579261514, | |
| "loss": 2.3977, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.005207849618134427, | |
| "grad_norm": 1.437606930732727, | |
| "learning_rate": 0.0001999866341390485, | |
| "loss": 2.4527, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.005555039592676722, | |
| "grad_norm": 1.4428914785385132, | |
| "learning_rate": 0.00019998479139898668, | |
| "loss": 2.4495, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.005902229567219017, | |
| "grad_norm": 2.573493719100952, | |
| "learning_rate": 0.00019998282970815832, | |
| "loss": 2.4216, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.006249419541761312, | |
| "grad_norm": 1.491316795349121, | |
| "learning_rate": 0.00019998074906889715, | |
| "loss": 2.4209, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.006596609516303607, | |
| "grad_norm": 1.9518392086029053, | |
| "learning_rate": 0.00019997854948367846, | |
| "loss": 2.4081, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.006943799490845903, | |
| "grad_norm": 1.6811418533325195, | |
| "learning_rate": 0.0001999762309551191, | |
| "loss": 2.4255, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.007290989465388197, | |
| "grad_norm": 1.316292643547058, | |
| "learning_rate": 0.00019997379348597744, | |
| "loss": 2.4039, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.007638179439930492, | |
| "grad_norm": 1.297400712966919, | |
| "learning_rate": 0.00019997123707915325, | |
| "loss": 2.4193, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.007985369414472789, | |
| "grad_norm": 1.5318177938461304, | |
| "learning_rate": 0.00019996856173768785, | |
| "loss": 2.4258, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.008332559389015082, | |
| "grad_norm": 2.240832567214966, | |
| "learning_rate": 0.00019996576746476413, | |
| "loss": 2.4457, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.008679749363557377, | |
| "grad_norm": 1.50482976436615, | |
| "learning_rate": 0.00019996285426370636, | |
| "loss": 2.4521, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.009026939338099673, | |
| "grad_norm": 1.1736887693405151, | |
| "learning_rate": 0.00019995982213798035, | |
| "loss": 2.4226, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.009374129312641968, | |
| "grad_norm": 1.489713430404663, | |
| "learning_rate": 0.00019995667109119335, | |
| "loss": 2.4314, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.009721319287184263, | |
| "grad_norm": 2.00687313079834, | |
| "learning_rate": 0.00019995340112709422, | |
| "loss": 2.4389, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.010068509261726559, | |
| "grad_norm": 1.5748944282531738, | |
| "learning_rate": 0.00019995001224957308, | |
| "loss": 2.4483, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.010415699236268854, | |
| "grad_norm": 1.7045289278030396, | |
| "learning_rate": 0.00019994650446266175, | |
| "loss": 2.4407, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.01076288921081115, | |
| "grad_norm": 1.3988068103790283, | |
| "learning_rate": 0.0001999428777705333, | |
| "loss": 2.462, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.011110079185353445, | |
| "grad_norm": 1.3608533143997192, | |
| "learning_rate": 0.00019993913217750245, | |
| "loss": 2.4472, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.011457269159895738, | |
| "grad_norm": 1.2952604293823242, | |
| "learning_rate": 0.00019993526768802525, | |
| "loss": 2.4427, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.011804459134438033, | |
| "grad_norm": 2.3562355041503906, | |
| "learning_rate": 0.0001999312843066992, | |
| "loss": 2.4659, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.012151649108980329, | |
| "grad_norm": 2.296459913253784, | |
| "learning_rate": 0.00019992718203826337, | |
| "loss": 2.4795, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.012498839083522624, | |
| "grad_norm": 1.3606270551681519, | |
| "learning_rate": 0.00019992296088759814, | |
| "loss": 2.463, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.01284602905806492, | |
| "grad_norm": 1.6714372634887695, | |
| "learning_rate": 0.00019991862085972536, | |
| "loss": 2.43, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.013193219032607215, | |
| "grad_norm": 2.1929798126220703, | |
| "learning_rate": 0.0001999141619598083, | |
| "loss": 2.4513, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.01354040900714951, | |
| "grad_norm": 1.7777063846588135, | |
| "learning_rate": 0.00019990958419315166, | |
| "loss": 2.472, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.013887598981691805, | |
| "grad_norm": 1.5554057359695435, | |
| "learning_rate": 0.00019990488756520164, | |
| "loss": 2.4663, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.0142347889562341, | |
| "grad_norm": 1.551933765411377, | |
| "learning_rate": 0.00019990007208154565, | |
| "loss": 2.5033, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.014581978930776394, | |
| "grad_norm": 1.9665030241012573, | |
| "learning_rate": 0.00019989513774791267, | |
| "loss": 2.4518, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.01492916890531869, | |
| "grad_norm": 1.5771666765213013, | |
| "learning_rate": 0.000199890084570173, | |
| "loss": 2.4703, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.015276358879860985, | |
| "grad_norm": 1.750036597251892, | |
| "learning_rate": 0.0001998849125543384, | |
| "loss": 2.495, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.01562354885440328, | |
| "grad_norm": 1.4305938482284546, | |
| "learning_rate": 0.00019987962170656188, | |
| "loss": 2.473, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.015970738828945577, | |
| "grad_norm": 1.410703420639038, | |
| "learning_rate": 0.00019987421203313799, | |
| "loss": 2.4629, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.01631792880348787, | |
| "grad_norm": 1.448388695716858, | |
| "learning_rate": 0.0001998686835405025, | |
| "loss": 2.4591, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.016665118778030164, | |
| "grad_norm": 1.7654149532318115, | |
| "learning_rate": 0.00019986303623523258, | |
| "loss": 2.4754, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.01701230875257246, | |
| "grad_norm": 1.8118611574172974, | |
| "learning_rate": 0.0001998572701240468, | |
| "loss": 2.4657, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.017359498727114755, | |
| "grad_norm": 1.8808069229125977, | |
| "learning_rate": 0.00019985138521380505, | |
| "loss": 2.4736, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.01770668870165705, | |
| "grad_norm": 1.5441018342971802, | |
| "learning_rate": 0.00019984538151150846, | |
| "loss": 2.4785, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.018053878676199345, | |
| "grad_norm": 1.6582081317901611, | |
| "learning_rate": 0.00019983925902429967, | |
| "loss": 2.4841, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.01840106865074164, | |
| "grad_norm": 1.5702968835830688, | |
| "learning_rate": 0.00019983301775946245, | |
| "loss": 2.4868, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.018748258625283936, | |
| "grad_norm": 2.0732314586639404, | |
| "learning_rate": 0.00019982665772442205, | |
| "loss": 2.4601, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.01909544859982623, | |
| "grad_norm": 1.4423972368240356, | |
| "learning_rate": 0.00019982017892674483, | |
| "loss": 2.4773, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.019442638574368527, | |
| "grad_norm": 1.9959121942520142, | |
| "learning_rate": 0.00019981358137413863, | |
| "loss": 2.4989, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.019789828548910822, | |
| "grad_norm": 1.7514522075653076, | |
| "learning_rate": 0.0001998068650744524, | |
| "loss": 2.4689, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.020137018523453117, | |
| "grad_norm": 1.6253585815429688, | |
| "learning_rate": 0.00019980003003567653, | |
| "loss": 2.4683, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.020484208497995413, | |
| "grad_norm": 1.9775470495224, | |
| "learning_rate": 0.0001997930762659425, | |
| "loss": 2.4787, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.020831398472537708, | |
| "grad_norm": 1.4767321348190308, | |
| "learning_rate": 0.00019978600377352324, | |
| "loss": 2.4865, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.021178588447080003, | |
| "grad_norm": 2.2066593170166016, | |
| "learning_rate": 0.00019977881256683273, | |
| "loss": 2.4826, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 0.0215257784216223, | |
| "grad_norm": 1.9816187620162964, | |
| "learning_rate": 0.00019977150265442626, | |
| "loss": 2.486, | |
| "step": 6200 | |
| }, | |
| { | |
| "epoch": 0.021872968396164594, | |
| "grad_norm": 1.573564052581787, | |
| "learning_rate": 0.0001997640740450004, | |
| "loss": 2.4893, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 0.02222015837070689, | |
| "grad_norm": 2.1582605838775635, | |
| "learning_rate": 0.00019975652674739285, | |
| "loss": 2.4896, | |
| "step": 6400 | |
| }, | |
| { | |
| "epoch": 0.02256734834524918, | |
| "grad_norm": 1.991675615310669, | |
| "learning_rate": 0.00019974886077058255, | |
| "loss": 2.5041, | |
| "step": 6500 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 288027, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 1.7839791959124787e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |