| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.2, |
| "eval_steps": 50, |
| "global_step": 750, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08, |
| "grad_norm": 0.05632242560386658, |
| "learning_rate": 0.00013297872340425532, |
| "loss": 1.8852, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.08, |
| "eval_loss": 1.707169532775879, |
| "eval_runtime": 27.6118, |
| "eval_samples_per_second": 3.622, |
| "eval_steps_per_second": 0.471, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.02606302499771118, |
| "learning_rate": 0.0002632978723404255, |
| "loss": 1.6036, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.16, |
| "eval_loss": 1.4855879545211792, |
| "eval_runtime": 27.6396, |
| "eval_samples_per_second": 3.618, |
| "eval_steps_per_second": 0.47, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 0.034023039042949677, |
| "learning_rate": 0.00039627659574468084, |
| "loss": 1.5186, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.24, |
| "eval_loss": 1.466215968132019, |
| "eval_runtime": 27.5933, |
| "eval_samples_per_second": 3.624, |
| "eval_steps_per_second": 0.471, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.04070857912302017, |
| "learning_rate": 0.0004967397747480735, |
| "loss": 1.4822, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.32, |
| "eval_loss": 1.4602761268615723, |
| "eval_runtime": 27.615, |
| "eval_samples_per_second": 3.621, |
| "eval_steps_per_second": 0.471, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 0.03537657856941223, |
| "learning_rate": 0.00048192056905749855, |
| "loss": 1.5035, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 1.4578460454940796, |
| "eval_runtime": 27.6799, |
| "eval_samples_per_second": 3.613, |
| "eval_steps_per_second": 0.47, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.040425803512334824, |
| "learning_rate": 0.00046710136336692356, |
| "loss": 1.4813, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.48, |
| "eval_loss": 1.4557801485061646, |
| "eval_runtime": 27.6578, |
| "eval_samples_per_second": 3.616, |
| "eval_steps_per_second": 0.47, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 0.03970955312252045, |
| "learning_rate": 0.00045228215767634857, |
| "loss": 1.4878, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.56, |
| "eval_loss": 1.4533815383911133, |
| "eval_runtime": 27.6598, |
| "eval_samples_per_second": 3.615, |
| "eval_steps_per_second": 0.47, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.03238854929804802, |
| "learning_rate": 0.0004374629519857736, |
| "loss": 1.4765, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_loss": 1.4522851705551147, |
| "eval_runtime": 27.5987, |
| "eval_samples_per_second": 3.623, |
| "eval_steps_per_second": 0.471, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 0.04000236839056015, |
| "learning_rate": 0.0004226437462951986, |
| "loss": 1.4803, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.72, |
| "eval_loss": 1.4484608173370361, |
| "eval_runtime": 27.6359, |
| "eval_samples_per_second": 3.618, |
| "eval_steps_per_second": 0.47, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.035757772624492645, |
| "learning_rate": 0.0004078245406046236, |
| "loss": 1.4925, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 1.4477622509002686, |
| "eval_runtime": 27.6496, |
| "eval_samples_per_second": 3.617, |
| "eval_steps_per_second": 0.47, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 0.039886392652988434, |
| "learning_rate": 0.0003930053349140486, |
| "loss": 1.49, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.88, |
| "eval_loss": 1.4466557502746582, |
| "eval_runtime": 27.6503, |
| "eval_samples_per_second": 3.617, |
| "eval_steps_per_second": 0.47, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.035769980400800705, |
| "learning_rate": 0.00037818612922347364, |
| "loss": 1.4888, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.96, |
| "eval_loss": 1.4460580348968506, |
| "eval_runtime": 27.6213, |
| "eval_samples_per_second": 3.62, |
| "eval_steps_per_second": 0.471, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.04, |
| "grad_norm": 0.039503153413534164, |
| "learning_rate": 0.00036336692353289865, |
| "loss": 1.4732, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.04, |
| "eval_loss": 1.4470006227493286, |
| "eval_runtime": 27.6084, |
| "eval_samples_per_second": 3.622, |
| "eval_steps_per_second": 0.471, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.12, |
| "grad_norm": 0.04102110490202904, |
| "learning_rate": 0.00034854771784232366, |
| "loss": 1.4677, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.12, |
| "eval_loss": 1.4475681781768799, |
| "eval_runtime": 27.6032, |
| "eval_samples_per_second": 3.623, |
| "eval_steps_per_second": 0.471, |
| "step": 700 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1875, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 5.641442504933376e+16, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
