| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001344628210299852, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.6892564205997043e-05, | |
| "eval_loss": 1.3629132509231567, | |
| "eval_runtime": 651.4742, | |
| "eval_samples_per_second": 24.033, | |
| "eval_steps_per_second": 12.017, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001344628210299852, | |
| "grad_norm": 0.958237886428833, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3946, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0002689256420599704, | |
| "grad_norm": 0.49982360005378723, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2357, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0002689256420599704, | |
| "eval_loss": 1.3428665399551392, | |
| "eval_runtime": 647.8287, | |
| "eval_samples_per_second": 24.168, | |
| "eval_steps_per_second": 12.085, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004033884630899556, | |
| "grad_norm": 0.8333525061607361, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1357, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005378512841199408, | |
| "grad_norm": 0.5812451243400574, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0984, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005378512841199408, | |
| "eval_loss": 1.2606666088104248, | |
| "eval_runtime": 646.9544, | |
| "eval_samples_per_second": 24.201, | |
| "eval_steps_per_second": 12.101, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000672314105149926, | |
| "grad_norm": 0.4732387363910675, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9479, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0008067769261799112, | |
| "grad_norm": 0.5627620816230774, | |
| "learning_rate": 5e-05, | |
| "loss": 1.298, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008067769261799112, | |
| "eval_loss": 1.2116531133651733, | |
| "eval_runtime": 644.377, | |
| "eval_samples_per_second": 24.298, | |
| "eval_steps_per_second": 12.15, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0009412397472098965, | |
| "grad_norm": 0.4738096296787262, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.0158, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0010757025682398816, | |
| "grad_norm": 0.47830018401145935, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.0883, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0010757025682398816, | |
| "eval_loss": 1.1898620128631592, | |
| "eval_runtime": 638.7298, | |
| "eval_samples_per_second": 24.513, | |
| "eval_steps_per_second": 12.257, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0012101653892698668, | |
| "grad_norm": 0.695751965045929, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0682, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.001344628210299852, | |
| "grad_norm": 0.46239423751831055, | |
| "learning_rate": 0.0, | |
| "loss": 0.9861, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001344628210299852, | |
| "eval_loss": 1.1852054595947266, | |
| "eval_runtime": 639.9704, | |
| "eval_samples_per_second": 24.465, | |
| "eval_steps_per_second": 12.233, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2229550527283200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |