avsolatorio/data-use-unsloth-phi-3.5-data-datause-climatechange-100epochs-1736734709-lora

{"epoch": 10.998917358354385, "global_step": 7612, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 1.3799044436544922e+18, "log_history": [{"loss": 0.3554, "grad_norm": 0.797683596611023, "learning_rate": 0.00017979476803006218, "epoch": 10.115481775532299, "step": 7000}, {"loss": 0.3396, "grad_norm": 0.8371628522872925, "learning_rate": 0.00017950570891747363, "epoch": 10.259833994947673, "step": 7100}, {"loss": 0.3479, "grad_norm": 0.8979386687278748, "learning_rate": 0.0001792166498048851, "epoch": 10.404186214363046, "step": 7200}, {"loss": 0.3581, "grad_norm": 0.9074283838272095, "learning_rate": 0.0001789275906922966, "epoch": 10.54853843377842, "step": 7300}, {"loss": 0.3727, "grad_norm": 0.716524064540863, "learning_rate": 0.00017863853157970807, "epoch": 10.692890653193793, "step": 7400}, {"loss": 0.3818, "grad_norm": 0.8861318230628967, "learning_rate": 0.00017834947246711953, "epoch": 10.837242872609167, "step": 7500}, {"loss": 0.3829, "grad_norm": 1.0592060089111328, "learning_rate": 0.000178060413354531, "epoch": 10.98159509202454, "step": 7600}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 9.998917358354385, "global_step": 6920, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 1.2530092064016384e+18, "log_history": [{"loss": 0.4632, "grad_norm": 0.7801975607872009, "learning_rate": 0.00018181818181818183, "epoch": 9.103933597979069, "step": 6300}, {"loss": 0.4178, "grad_norm": 0.8344607949256897, "learning_rate": 0.0001815291227055933, "epoch": 9.248285817394443, "step": 6400}, {"loss": 0.4257, "grad_norm": 0.6335723400115967, "learning_rate": 0.00018124006359300477, "epoch": 9.392638036809815, "step": 6500}, {"loss": 0.4531, "grad_norm": 0.8514361381530762, "learning_rate": 0.00018095100448041625, "epoch": 9.53699025622519, "step": 6600}, {"loss": 0.4573, "grad_norm": 0.9573537111282349, "learning_rate": 0.00018066194536782773, "epoch": 9.681342475640562, "step": 6700}, {"loss": 0.4761, "grad_norm": 0.8129424452781677, "learning_rate": 0.0001803728862552392, "epoch": 9.825694695055937, "step": 6800}, {"loss": 0.4748, "grad_norm": 0.7682424783706665, "learning_rate": 0.0001800838271426507, "epoch": 9.97004691447131, "step": 6900}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 8.998917358354385, "global_step": 6228, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 1.1258327145150259e+18, "log_history": [{"loss": 0.5982, "grad_norm": 1.0791505575180054, "learning_rate": 0.0001838415956063015, "epoch": 8.092385420425838, "step": 5600}, {"loss": 0.5242, "grad_norm": 0.6707946062088013, "learning_rate": 0.00018355253649371297, "epoch": 8.236737639841213, "step": 5700}, {"loss": 0.5437, "grad_norm": 0.8628165125846863, "learning_rate": 0.00018326347738112443, "epoch": 8.381089859256585, "step": 5800}, {"loss": 0.5533, "grad_norm": 0.6727371215820312, "learning_rate": 0.0001829744182685359, "epoch": 8.52544207867196, "step": 5900}, {"loss": 0.5708, "grad_norm": 0.6793197393417358, "learning_rate": 0.0001826853591559474, "epoch": 8.669794298087332, "step": 6000}, {"loss": 0.5709, "grad_norm": 0.7611024975776672, "learning_rate": 0.00018239630004335887, "epoch": 8.814146517502707, "step": 6100}, {"loss": 0.587, "grad_norm": 0.8184096217155457, "learning_rate": 0.00018210724093077035, "epoch": 8.95849873691808, "step": 6200}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 7.998917358354385, "global_step": 5536, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 9.985861116029952e+17, "log_history": [{"loss": 0.7255, "grad_norm": 0.5299221873283386, "learning_rate": 0.00018586500939442118, "epoch": 7.080837242872609, "step": 4900}, {"loss": 0.6313, "grad_norm": 0.7880389094352722, "learning_rate": 0.00018557595028183263, "epoch": 7.225189462287982, "step": 5000}, {"loss": 0.666, "grad_norm": 0.6784034371376038, "learning_rate": 0.0001852868911692441, "epoch": 7.369541681703356, "step": 5100}, {"loss": 0.686, "grad_norm": 0.7515205144882202, "learning_rate": 0.0001849978320566556, "epoch": 7.513893901118729, "step": 5200}, {"loss": 0.6991, "grad_norm": 0.6742441058158875, "learning_rate": 0.00018470877294406708, "epoch": 7.658246120534104, "step": 5300}, {"loss": 0.6949, "grad_norm": 0.6748549938201904, "learning_rate": 0.00018441971383147853, "epoch": 7.802598339949476, "step": 5400}, {"loss": 0.6901, "grad_norm": 0.6470287442207336, "learning_rate": 0.00018413065471889, "epoch": 7.946950559364851, "step": 5500}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 6.998917358354385, "global_step": 4844, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 8.712008626747392e+17, "log_history": [{"loss": 0.8881, "grad_norm": 0.40097475051879883, "learning_rate": 0.00018788842318254084, "epoch": 6.06928906531938, "step": 4200}, {"loss": 0.7876, "grad_norm": 0.49134522676467896, "learning_rate": 0.00018759936406995232, "epoch": 6.213641284734753, "step": 4300}, {"loss": 0.7891, "grad_norm": 0.6759152412414551, "learning_rate": 0.0001873103049573638, "epoch": 6.3579935041501265, "step": 4400}, {"loss": 0.8066, "grad_norm": 0.4952390193939209, "learning_rate": 0.00018702124584477528, "epoch": 6.5023457235655, "step": 4500}, {"loss": 0.8006, "grad_norm": 0.45524337887763977, "learning_rate": 0.00018673218673218673, "epoch": 6.6466979429808735, "step": 4600}, {"loss": 0.8057, "grad_norm": 0.5147778987884521, "learning_rate": 0.00018644312761959822, "epoch": 6.791050162396247, "step": 4700}, {"loss": 0.8051, "grad_norm": 0.5864388346672058, "learning_rate": 0.0001861540685070097, "epoch": 6.93540238181162, "step": 4800}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 5.998917358354385, "global_step": 4152, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 7.442672152069325e+17, "log_history": [{"loss": 1.0256, "grad_norm": 0.37456730008125305, "learning_rate": 0.0001899118369706605, "epoch": 5.057740887766149, "step": 3500}, {"loss": 0.9026, "grad_norm": 0.529521644115448, "learning_rate": 0.00018962277785807198, "epoch": 5.202093107181523, "step": 3600}, {"loss": 0.9225, "grad_norm": 0.5069609880447388, "learning_rate": 0.00018933371874548346, "epoch": 5.346445326596896, "step": 3700}, {"loss": 0.9274, "grad_norm": 0.4902782440185547, "learning_rate": 0.00018904465963289494, "epoch": 5.49079754601227, "step": 3800}, {"loss": 0.9282, "grad_norm": 0.3776276707649231, "learning_rate": 0.00018875560052030642, "epoch": 5.635149765427643, "step": 3900}, {"loss": 0.9519, "grad_norm": 0.4415137767791748, "learning_rate": 0.0001884665414077179, "epoch": 5.779501984843017, "step": 4000}, {"loss": 0.936, "grad_norm": 0.4424417316913605, "learning_rate": 0.00018817748229512938, "epoch": 5.92385420425839, "step": 4100}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 4.998917358354385, "global_step": 3460, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 6.17767427552809e+17, "log_history": [{"loss": 1.1179, "grad_norm": 0.35473960638046265, "learning_rate": 0.00019193525075878018, "epoch": 4.046192710212919, "step": 2800}, {"loss": 1.0489, "grad_norm": 0.4328194856643677, "learning_rate": 0.00019164619164619166, "epoch": 4.190544929628293, "step": 2900}, {"loss": 1.0561, "grad_norm": 0.29221799969673157, "learning_rate": 0.00019135713253360312, "epoch": 4.334897149043666, "step": 3000}, {"loss": 1.0269, "grad_norm": 0.34269750118255615, "learning_rate": 0.0001910680734210146, "epoch": 4.47924936845904, "step": 3100}, {"loss": 1.0352, "grad_norm": 0.3695838451385498, "learning_rate": 0.00019077901430842608, "epoch": 4.623601587874414, "step": 3200}, {"loss": 1.0781, "grad_norm": 0.43560290336608887, "learning_rate": 0.00019048995519583756, "epoch": 4.767953807289787, "step": 3300}, {"loss": 1.0739, "grad_norm": 0.387684166431427, "learning_rate": 0.000190200896083249, "epoch": 4.912306026705161, "step": 3400}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 3.998917358354385, "global_step": 2768, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 4.904820541893427e+17, "log_history": [{"loss": 1.2543, "grad_norm": 0.29482826590538025, "learning_rate": 0.00019395866454689987, "epoch": 3.03464453265969, "step": 2100}, {"loss": 1.1722, "grad_norm": 0.27606767416000366, "learning_rate": 0.00019366960543431132, "epoch": 3.1789967520750633, "step": 2200}, {"loss": 1.1597, "grad_norm": 0.25408926606178284, "learning_rate": 0.0001933805463217228, "epoch": 3.3233489714904367, "step": 2300}, {"loss": 1.194, "grad_norm": 0.31680524349212646, "learning_rate": 0.00019309148720913428, "epoch": 3.46770119090581, "step": 2400}, {"loss": 1.1561, "grad_norm": 0.25974026322364807, "learning_rate": 0.00019280242809654576, "epoch": 3.6120534103211837, "step": 2500}, {"loss": 1.1746, "grad_norm": 0.30843597650527954, "learning_rate": 0.00019251336898395722, "epoch": 3.756405629736557, "step": 2600}, {"loss": 1.1837, "grad_norm": 0.6003233790397644, "learning_rate": 0.0001922243098713687, "epoch": 3.9007578491519306, "step": 2700}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 2.998917358354385, "global_step": 2076, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 3.6349491160387584e+17, "log_history": [{"loss": 1.3759, "grad_norm": 0.20204421877861023, "learning_rate": 0.00019598207833501952, "epoch": 2.0230963551064596, "step": 1400}, {"loss": 1.2868, "grad_norm": 0.2579204738140106, "learning_rate": 0.000195693019222431, "epoch": 2.167448574521833, "step": 1500}, {"loss": 1.3018, "grad_norm": 0.24711860716342926, "learning_rate": 0.00019540396010984249, "epoch": 2.311800793937207, "step": 1600}, {"loss": 1.302, "grad_norm": 0.2458779215812683, "learning_rate": 0.00019511490099725397, "epoch": 2.4561530133525804, "step": 1700}, {"loss": 1.2886, "grad_norm": 0.42433080077171326, "learning_rate": 0.00019482584188466542, "epoch": 2.600505232767954, "step": 1800}, {"loss": 1.2701, "grad_norm": 0.262311190366745, "learning_rate": 0.0001945367827720769, "epoch": 2.7448574521833273, "step": 1900}, {"loss": 1.2595, "grad_norm": 0.26452723145484924, "learning_rate": 0.00019424772365948838, "epoch": 2.889209671598701, "step": 2000}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 1.9989173583543847, "global_step": 1384, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 2.3685724343605248e+17, "log_history": [{"loss": 1.4629, "grad_norm": 0.17430748045444489, "learning_rate": 0.00019800549212313918, "epoch": 1.0115481775532298, "step": 700}, {"loss": 1.3696, "grad_norm": 0.19151850044727325, "learning_rate": 0.00019771643301055066, "epoch": 1.1559003969686035, "step": 800}, {"loss": 1.3833, "grad_norm": 0.1917247176170349, "learning_rate": 0.00019742737389796214, "epoch": 1.300252616383977, "step": 900}, {"loss": 1.3895, "grad_norm": 0.20224860310554504, "learning_rate": 0.00019713831478537363, "epoch": 1.4446048357993504, "step": 1000}, {"loss": 1.3489, "grad_norm": 0.2021542191505432, "learning_rate": 0.0001968492556727851, "epoch": 1.588957055214724, "step": 1100}, {"loss": 1.4097, "grad_norm": 0.18438276648521423, "learning_rate": 0.0001965601965601966, "epoch": 1.7333092746300975, "step": 1200}, {"loss": 1.3675, "grad_norm": 0.2104136198759079, "learning_rate": 0.00019627113744760804, "epoch": 1.877661494045471, "step": 1300}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 0.9989173583543847, "global_step": 692, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 1.0906141497679872e+17, "log_history": [{"loss": 1.6084, "grad_norm": 0.1420315057039261, "learning_rate": 0.00019973984679867032, "epoch": 0.14435221941537352, "step": 100}, {"loss": 1.5004, "grad_norm": 0.17376014590263367, "learning_rate": 0.0001994507876860818, "epoch": 0.28870443883074703, "step": 200}, {"loss": 1.4777, "grad_norm": 0.16006237268447876, "learning_rate": 0.00019916172857349328, "epoch": 0.43305665824612055, "step": 300}, {"loss": 1.4575, "grad_norm": 0.15284836292266846, "learning_rate": 0.00019887266946090476, "epoch": 0.5774088776614941, "step": 400}, {"loss": 1.4788, "grad_norm": 0.16268718242645264, "learning_rate": 0.00019858361034831622, "epoch": 0.7217610970768675, "step": 500}, {"loss": 1.4451, "grad_norm": 0.1624559760093689, "learning_rate": 0.0001982945512357277, "epoch": 0.8661133164922411, "step": 600}], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": true, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 0, "global_step": 0, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 0, "log_history": [], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": false, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

{"epoch": 0, "global_step": 0, "max_steps": 69200, "logging_steps": 100, "eval_steps": 500, "save_steps": 500, "train_batch_size": 2, "num_train_epochs": 100, "num_input_tokens_seen": 0, "total_flos": 0, "log_history": [], "best_metric": null, "best_model_checkpoint": null, "is_local_process_zero": true, "is_world_process_zero": true, "is_hyper_param_search": false, "trial_name": null, "trial_params": null, "stateful_callbacks": {"TrainerControl": {"args": {"should_training_stop": false, "should_epoch_stop": false, "should_save": false, "should_evaluate": false, "should_log": false}, "attributes": {}}}} (Trained with Unsloth)

Upload README.md with huggingface_hub

initial commit