| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 155, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0645682001614205, |
| "grad_norm": 0.8069110898977796, |
| "learning_rate": 5.625e-06, |
| "loss": 0.6695831418037415, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.129136400322841, |
| "grad_norm": 0.4330663610600958, |
| "learning_rate": 9.9885108930818e-06, |
| "loss": 0.5777108073234558, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.1937046004842615, |
| "grad_norm": 0.2754324714654337, |
| "learning_rate": 9.785725615782262e-06, |
| "loss": 0.5425556500752767, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.258272800645682, |
| "grad_norm": 0.22721648542536138, |
| "learning_rate": 9.33951351964525e-06, |
| "loss": 0.5174514055252075, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3228410008071025, |
| "grad_norm": 0.23342764181076078, |
| "learning_rate": 8.672571265492944e-06, |
| "loss": 0.5092498779296875, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.387409200968523, |
| "grad_norm": 0.24311945587345685, |
| "learning_rate": 7.818822994471504e-06, |
| "loss": 0.4979246457417806, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4519774011299435, |
| "grad_norm": 0.3383109105717731, |
| "learning_rate": 6.8216947703354815e-06, |
| "loss": 0.49263341086251394, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.516545601291364, |
| "grad_norm": 0.4587467243203668, |
| "learning_rate": 5.731905704680834e-06, |
| "loss": 0.48938480019569397, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.5811138014527845, |
| "grad_norm": 0.2835512697183779, |
| "learning_rate": 4.6048881199502265e-06, |
| "loss": 0.4843639267815484, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.645682001614205, |
| "grad_norm": 0.2506103669101136, |
| "learning_rate": 3.497967974096647e-06, |
| "loss": 0.48187875747680664, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7102502017756255, |
| "grad_norm": 0.2406265586311052, |
| "learning_rate": 2.4674489651264433e-06, |
| "loss": 0.48817190527915955, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.774818401937046, |
| "grad_norm": 0.23065794023843042, |
| "learning_rate": 1.5657486330836786e-06, |
| "loss": 0.48073236147562665, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.8393866020984665, |
| "grad_norm": 0.22029963575446374, |
| "learning_rate": 8.387321321781977e-07, |
| "loss": 0.4764113128185272, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.903954802259887, |
| "grad_norm": 0.2151258135358492, |
| "learning_rate": 3.233792912313943e-07, |
| "loss": 0.47532830238342283, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.9685230024213075, |
| "grad_norm": 0.22455673688429373, |
| "learning_rate": 4.590362784169022e-08, |
| "loss": 0.48181764284769696, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 155, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 3, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.4414173445100667e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
