| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005849834742168534, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011699669484337067, | |
| "eval_loss": 6.246862411499023, | |
| "eval_runtime": 1230.1211, | |
| "eval_samples_per_second": 2.926, | |
| "eval_steps_per_second": 1.463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005849834742168534, | |
| "grad_norm": 102.26433563232422, | |
| "learning_rate": 5e-05, | |
| "loss": 23.1351, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0011699669484337067, | |
| "grad_norm": 82.44818878173828, | |
| "learning_rate": 0.0001, | |
| "loss": 14.923, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011699669484337067, | |
| "eval_loss": 2.5302603244781494, | |
| "eval_runtime": 1031.1683, | |
| "eval_samples_per_second": 3.49, | |
| "eval_steps_per_second": 1.746, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00175495042265056, | |
| "grad_norm": 57.642765045166016, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 7.7928, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0023399338968674134, | |
| "grad_norm": 54.19350051879883, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 6.52, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0023399338968674134, | |
| "eval_loss": 1.5054985284805298, | |
| "eval_runtime": 885.164, | |
| "eval_samples_per_second": 4.066, | |
| "eval_steps_per_second": 2.034, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.002924917371084267, | |
| "grad_norm": 46.926055908203125, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 6.1166, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00350990084530112, | |
| "grad_norm": 50.563045501708984, | |
| "learning_rate": 5e-05, | |
| "loss": 5.7146, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00350990084530112, | |
| "eval_loss": 1.431323528289795, | |
| "eval_runtime": 718.0375, | |
| "eval_samples_per_second": 5.012, | |
| "eval_steps_per_second": 2.507, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004094884319517974, | |
| "grad_norm": 9.158976554870605, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.6131, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.004679867793734827, | |
| "grad_norm": 12.215734481811523, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.6891, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.004679867793734827, | |
| "eval_loss": 1.4018374681472778, | |
| "eval_runtime": 725.6503, | |
| "eval_samples_per_second": 4.96, | |
| "eval_steps_per_second": 2.481, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.00526485126795168, | |
| "grad_norm": 7.4448161125183105, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.3698, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.005849834742168534, | |
| "grad_norm": 11.222515106201172, | |
| "learning_rate": 0.0, | |
| "loss": 5.4539, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005849834742168534, | |
| "eval_loss": 1.3965027332305908, | |
| "eval_runtime": 730.5266, | |
| "eval_samples_per_second": 4.927, | |
| "eval_steps_per_second": 2.464, | |
| "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": 9245343740854272.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |