| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0243116756822464, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000121558378411232, | |
| "eval_loss": 2.51324725151062, | |
| "eval_runtime": 129.2942, | |
| "eval_samples_per_second": 26.792, | |
| "eval_steps_per_second": 13.396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00121558378411232, | |
| "grad_norm": 1.9220033884048462, | |
| "learning_rate": 0.0002, | |
| "loss": 9.2311, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00243116756822464, | |
| "grad_norm": 2.4667861461639404, | |
| "learning_rate": 0.0002, | |
| "loss": 9.3961, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0036467513523369597, | |
| "grad_norm": 2.1678335666656494, | |
| "learning_rate": 0.0002, | |
| "loss": 9.2295, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00486233513644928, | |
| "grad_norm": 1.7435227632522583, | |
| "learning_rate": 0.0002, | |
| "loss": 9.2995, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0060779189205616, | |
| "grad_norm": 1.7226349115371704, | |
| "learning_rate": 0.0002, | |
| "loss": 8.9876, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0060779189205616, | |
| "eval_loss": 2.2176895141601562, | |
| "eval_runtime": 129.241, | |
| "eval_samples_per_second": 26.803, | |
| "eval_steps_per_second": 13.401, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007293502704673919, | |
| "grad_norm": 1.1817125082015991, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0394, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00850908648878624, | |
| "grad_norm": 1.4283983707427979, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0866, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.00972467027289856, | |
| "grad_norm": 1.7030812501907349, | |
| "learning_rate": 0.0002, | |
| "loss": 8.8661, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.010940254057010879, | |
| "grad_norm": 1.697030782699585, | |
| "learning_rate": 0.0002, | |
| "loss": 8.8937, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0121558378411232, | |
| "grad_norm": 1.6287360191345215, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0157, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0121558378411232, | |
| "eval_loss": 2.199361801147461, | |
| "eval_runtime": 129.2644, | |
| "eval_samples_per_second": 26.798, | |
| "eval_steps_per_second": 13.399, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.01337142162523552, | |
| "grad_norm": 1.7065634727478027, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0676, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.014587005409347839, | |
| "grad_norm": 2.568800210952759, | |
| "learning_rate": 0.0002, | |
| "loss": 8.584, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.01580258919346016, | |
| "grad_norm": 2.7793874740600586, | |
| "learning_rate": 0.0002, | |
| "loss": 8.6535, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01701817297757248, | |
| "grad_norm": 2.116802453994751, | |
| "learning_rate": 0.0002, | |
| "loss": 8.6239, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0182337567616848, | |
| "grad_norm": 1.6645129919052124, | |
| "learning_rate": 0.0002, | |
| "loss": 8.5241, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0182337567616848, | |
| "eval_loss": 2.1867380142211914, | |
| "eval_runtime": 129.2587, | |
| "eval_samples_per_second": 26.799, | |
| "eval_steps_per_second": 13.399, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01944934054579712, | |
| "grad_norm": 1.7567479610443115, | |
| "learning_rate": 0.0002, | |
| "loss": 8.761, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.020664924329909438, | |
| "grad_norm": 1.3298070430755615, | |
| "learning_rate": 0.0002, | |
| "loss": 8.6619, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.021880508114021757, | |
| "grad_norm": 1.3300223350524902, | |
| "learning_rate": 0.0002, | |
| "loss": 8.9402, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02309609189813408, | |
| "grad_norm": 1.8174155950546265, | |
| "learning_rate": 0.0002, | |
| "loss": 8.7659, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0243116756822464, | |
| "grad_norm": 1.6860878467559814, | |
| "learning_rate": 0.0002, | |
| "loss": 9.0848, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0243116756822464, | |
| "eval_loss": 2.1836845874786377, | |
| "eval_runtime": 129.2197, | |
| "eval_samples_per_second": 26.807, | |
| "eval_steps_per_second": 13.404, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.762410749113139e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |