| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.6802721088435374, |
| "eval_steps": 30, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.045351473922902494, |
| "grad_norm": 0.5955151915550232, |
| "learning_rate": 0.00019962469712828614, |
| "loss": 0.4111457824707031, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.09070294784580499, |
| "grad_norm": 0.5896233320236206, |
| "learning_rate": 0.00019543482507085482, |
| "loss": 0.35993859767913816, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.1360544217687075, |
| "grad_norm": 0.48774707317352295, |
| "learning_rate": 0.00018678252666130013, |
| "loss": 0.38935122489929197, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.1360544217687075, |
| "eval_loss": 0.5217297077178955, |
| "eval_runtime": 2.0775, |
| "eval_samples_per_second": 34.657, |
| "eval_steps_per_second": 8.664, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.18140589569160998, |
| "grad_norm": 0.4432049095630646, |
| "learning_rate": 0.00017407237375691392, |
| "loss": 0.3316951274871826, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.22675736961451248, |
| "grad_norm": 0.40836411714553833, |
| "learning_rate": 0.0001578986789811849, |
| "loss": 0.31510772705078127, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.272108843537415, |
| "grad_norm": 0.3234673738479614, |
| "learning_rate": 0.00013901770632605547, |
| "loss": 0.3653845310211182, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.272108843537415, |
| "eval_loss": 0.5070984363555908, |
| "eval_runtime": 2.0635, |
| "eval_samples_per_second": 34.891, |
| "eval_steps_per_second": 8.723, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.31746031746031744, |
| "grad_norm": 0.28090140223503113, |
| "learning_rate": 0.00011831230908818563, |
| "loss": 0.2907076835632324, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.36281179138321995, |
| "grad_norm": 0.33969420194625854, |
| "learning_rate": 9.675064863002196e-05, |
| "loss": 0.3239952325820923, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.40816326530612246, |
| "grad_norm": 0.3883151113986969, |
| "learning_rate": 7.534092423052381e-05, |
| "loss": 0.39945359230041505, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.40816326530612246, |
| "eval_loss": 0.49975717067718506, |
| "eval_runtime": 2.0811, |
| "eval_samples_per_second": 34.597, |
| "eval_steps_per_second": 8.649, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.45351473922902497, |
| "grad_norm": 0.37783923745155334, |
| "learning_rate": 5.5084230807412126e-05, |
| "loss": 0.33277587890625, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4988662131519274, |
| "grad_norm": 0.44748321175575256, |
| "learning_rate": 3.6927748831453836e-05, |
| "loss": 0.3025733470916748, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.54421768707483, |
| "grad_norm": 0.39024776220321655, |
| "learning_rate": 2.1720455220364444e-05, |
| "loss": 0.30908067226409913, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.54421768707483, |
| "eval_loss": 0.4952836036682129, |
| "eval_runtime": 2.0845, |
| "eval_samples_per_second": 34.541, |
| "eval_steps_per_second": 8.635, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5895691609977324, |
| "grad_norm": 0.39623892307281494, |
| "learning_rate": 1.0173426121705576e-05, |
| "loss": 0.3232832193374634, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.6349206349206349, |
| "grad_norm": 0.3841199576854706, |
| "learning_rate": 2.826587782529444e-06, |
| "loss": 0.3398961782455444, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6802721088435374, |
| "grad_norm": 0.4336070120334625, |
| "learning_rate": 2.347019815158724e-08, |
| "loss": 0.34069836139678955, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6802721088435374, |
| "eval_loss": 0.49498093128204346, |
| "eval_runtime": 2.0755, |
| "eval_samples_per_second": 34.691, |
| "eval_steps_per_second": 8.673, |
| "step": 150 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 150, |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4361616479379456.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
