| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0027162103433289874, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001086484137331595, | |
| "grad_norm": 1.5099513530731201, | |
| "learning_rate": 1e-05, | |
| "loss": 10.4046, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001086484137331595, | |
| "eval_loss": 10.412325859069824, | |
| "eval_runtime": 49.9215, | |
| "eval_samples_per_second": 155.264, | |
| "eval_steps_per_second": 19.41, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000217296827466319, | |
| "grad_norm": 1.6217904090881348, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3875, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003259452411994785, | |
| "grad_norm": 1.2565022706985474, | |
| "learning_rate": 3e-05, | |
| "loss": 10.4123, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.000434593654932638, | |
| "grad_norm": 1.4051614999771118, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3964, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005432420686657974, | |
| "grad_norm": 1.3535511493682861, | |
| "learning_rate": 5e-05, | |
| "loss": 10.4142, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000651890482398957, | |
| "grad_norm": 1.4999443292617798, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3977, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007605388961321165, | |
| "grad_norm": 1.3049250841140747, | |
| "learning_rate": 7e-05, | |
| "loss": 10.432, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000869187309865276, | |
| "grad_norm": 1.4855458736419678, | |
| "learning_rate": 8e-05, | |
| "loss": 10.4005, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0009778357235984355, | |
| "grad_norm": 1.406107783317566, | |
| "learning_rate": 9e-05, | |
| "loss": 10.4181, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009778357235984355, | |
| "eval_loss": 10.399271011352539, | |
| "eval_runtime": 51.0349, | |
| "eval_samples_per_second": 151.877, | |
| "eval_steps_per_second": 18.987, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0010864841373315949, | |
| "grad_norm": 1.486843466758728, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3952, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011951325510647544, | |
| "grad_norm": 1.6207181215286255, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3736, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.001303780964797914, | |
| "grad_norm": 1.467222809791565, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3963, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0014124293785310734, | |
| "grad_norm": 1.4670981168746948, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3987, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.001521077792264233, | |
| "grad_norm": 1.519575834274292, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.373, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0016297262059973925, | |
| "grad_norm": 1.5052906274795532, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.3953, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001738374619730552, | |
| "grad_norm": 1.284813404083252, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3941, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0018470230334637113, | |
| "grad_norm": 1.4351565837860107, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3775, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.001955671447196871, | |
| "grad_norm": 1.5797349214553833, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3798, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001955671447196871, | |
| "eval_loss": 10.36672306060791, | |
| "eval_runtime": 50.7013, | |
| "eval_samples_per_second": 152.876, | |
| "eval_steps_per_second": 19.112, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0020643198609300306, | |
| "grad_norm": 1.5637619495391846, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3719, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0021729682746631897, | |
| "grad_norm": 1.66817045211792, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3421, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0022816166883963492, | |
| "grad_norm": 1.4857240915298462, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3808, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0023902651021295088, | |
| "grad_norm": 1.6014432907104492, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3393, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0024989135158626683, | |
| "grad_norm": 1.5560365915298462, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.3411, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.002607561929595828, | |
| "grad_norm": 1.60709547996521, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3514, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0027162103433289874, | |
| "grad_norm": 1.4551864862442017, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3411, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1307561164800.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |