| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04657661853749418, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009315323707498836, | |
| "eval_loss": 2.67449688911438, | |
| "eval_runtime": 54.9548, | |
| "eval_samples_per_second": 8.243, | |
| "eval_steps_per_second": 4.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004657661853749418, | |
| "grad_norm": 1.050082802772522, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3571, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009315323707498836, | |
| "grad_norm": 1.03178071975708, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2236, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009315323707498836, | |
| "eval_loss": 2.541896104812622, | |
| "eval_runtime": 55.3938, | |
| "eval_samples_per_second": 8.178, | |
| "eval_steps_per_second": 4.098, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013972985561248253, | |
| "grad_norm": 1.6759586334228516, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.084, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018630647414997672, | |
| "grad_norm": 1.6972988843917847, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2981, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018630647414997672, | |
| "eval_loss": 2.2054669857025146, | |
| "eval_runtime": 55.6666, | |
| "eval_samples_per_second": 8.138, | |
| "eval_steps_per_second": 4.078, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02328830926874709, | |
| "grad_norm": 2.279262065887451, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0858, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.027945971122496506, | |
| "grad_norm": 2.0147440433502197, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9067, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027945971122496506, | |
| "eval_loss": 2.0615034103393555, | |
| "eval_runtime": 55.7005, | |
| "eval_samples_per_second": 8.133, | |
| "eval_steps_per_second": 4.075, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.032603632976245925, | |
| "grad_norm": 2.2418673038482666, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9613, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.037261294829995344, | |
| "grad_norm": 2.235062599182129, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.933, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.037261294829995344, | |
| "eval_loss": 2.0007143020629883, | |
| "eval_runtime": 55.7249, | |
| "eval_samples_per_second": 8.129, | |
| "eval_steps_per_second": 4.074, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04191895668374476, | |
| "grad_norm": 1.7607734203338623, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.893, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04657661853749418, | |
| "grad_norm": 2.078504800796509, | |
| "learning_rate": 0.0, | |
| "loss": 1.7617, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04657661853749418, | |
| "eval_loss": 1.9849607944488525, | |
| "eval_runtime": 55.6865, | |
| "eval_samples_per_second": 8.135, | |
| "eval_steps_per_second": 4.076, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |