| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0005949264670886678, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.3797058683546713e-05, | |
| "grad_norm": 16.747493743896484, | |
| "learning_rate": 1e-05, | |
| "loss": 11.8717, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.3797058683546713e-05, | |
| "eval_loss": 12.016156196594238, | |
| "eval_runtime": 3849.7025, | |
| "eval_samples_per_second": 9.192, | |
| "eval_steps_per_second": 1.149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.7594117367093426e-05, | |
| "grad_norm": 16.200801849365234, | |
| "learning_rate": 2e-05, | |
| "loss": 12.1197, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.139117605064014e-05, | |
| "grad_norm": 16.915584564208984, | |
| "learning_rate": 3e-05, | |
| "loss": 12.489, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.518823473418685e-05, | |
| "grad_norm": 17.902099609375, | |
| "learning_rate": 4e-05, | |
| "loss": 11.8387, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00011898529341773356, | |
| "grad_norm": 21.415821075439453, | |
| "learning_rate": 5e-05, | |
| "loss": 11.0785, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00014278235210128028, | |
| "grad_norm": 20.89607810974121, | |
| "learning_rate": 6e-05, | |
| "loss": 10.1305, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000166579410784827, | |
| "grad_norm": 16.76231575012207, | |
| "learning_rate": 7e-05, | |
| "loss": 7.9387, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001903764694683737, | |
| "grad_norm": 18.694364547729492, | |
| "learning_rate": 8e-05, | |
| "loss": 6.5209, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00021417352815192043, | |
| "grad_norm": 21.288978576660156, | |
| "learning_rate": 9e-05, | |
| "loss": 4.8662, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00021417352815192043, | |
| "eval_loss": 2.87481951713562, | |
| "eval_runtime": 3857.1064, | |
| "eval_samples_per_second": 9.174, | |
| "eval_steps_per_second": 1.147, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00023797058683546713, | |
| "grad_norm": 17.777185440063477, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7722, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00026176764551901383, | |
| "grad_norm": 15.348291397094727, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.9194, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00028556470420256055, | |
| "grad_norm": 12.259586334228516, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.8865, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003093617628861073, | |
| "grad_norm": 7.980026721954346, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.3215, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000333158821569654, | |
| "grad_norm": 12.922357559204102, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.433, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0003569558802532007, | |
| "grad_norm": 7.93162202835083, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.2306, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0003807529389367474, | |
| "grad_norm": 10.139382362365723, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.3991, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00040454999762029413, | |
| "grad_norm": 4.613278865814209, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 0.1883, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.00042834705630384086, | |
| "grad_norm": 5.257633209228516, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.2161, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00042834705630384086, | |
| "eval_loss": 0.18698039650917053, | |
| "eval_runtime": 3850.1903, | |
| "eval_samples_per_second": 9.191, | |
| "eval_steps_per_second": 1.149, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0004521441149873876, | |
| "grad_norm": 3.6496686935424805, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.193, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00047594117367093426, | |
| "grad_norm": 10.557854652404785, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.3724, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000499738232354481, | |
| "grad_norm": 6.450751304626465, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.2764, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0005235352910380277, | |
| "grad_norm": 2.2247400283813477, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.1977, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0005473323497215744, | |
| "grad_norm": 6.7696146965026855, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 0.3192, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0005711294084051211, | |
| "grad_norm": 10.131149291992188, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.5362, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005949264670886678, | |
| "grad_norm": 5.705859184265137, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2824, | |
| "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": 1.85471820890112e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |