| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0023347575354299454, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.669515070859891e-05, | |
| "eval_loss": 3.852412462234497, | |
| "eval_runtime": 1236.6296, | |
| "eval_samples_per_second": 7.292, | |
| "eval_steps_per_second": 3.646, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00023347575354299455, | |
| "grad_norm": 4.815019607543945, | |
| "learning_rate": 5e-05, | |
| "loss": 3.556, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004669515070859891, | |
| "grad_norm": 6.179628372192383, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0412, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004669515070859891, | |
| "eval_loss": 2.0145978927612305, | |
| "eval_runtime": 1246.3355, | |
| "eval_samples_per_second": 7.236, | |
| "eval_steps_per_second": 3.618, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007004272606289837, | |
| "grad_norm": 3.883136749267578, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4828, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0009339030141719782, | |
| "grad_norm": 5.323849678039551, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8697, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009339030141719782, | |
| "eval_loss": 0.5890653729438782, | |
| "eval_runtime": 1241.6779, | |
| "eval_samples_per_second": 7.263, | |
| "eval_steps_per_second": 3.631, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011673787677149727, | |
| "grad_norm": 4.373797416687012, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.449, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0014008545212579673, | |
| "grad_norm": 4.233983516693115, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4205, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0014008545212579673, | |
| "eval_loss": 0.35735270380973816, | |
| "eval_runtime": 1243.4607, | |
| "eval_samples_per_second": 7.252, | |
| "eval_steps_per_second": 3.626, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001634330274800962, | |
| "grad_norm": 4.750127792358398, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.409, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0018678060283439564, | |
| "grad_norm": 3.254962205886841, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.3198, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0018678060283439564, | |
| "eval_loss": 0.2902105748653412, | |
| "eval_runtime": 1241.3536, | |
| "eval_samples_per_second": 7.265, | |
| "eval_steps_per_second": 3.632, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002101281781886951, | |
| "grad_norm": 2.525123357772827, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.3341, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0023347575354299454, | |
| "grad_norm": 3.7383229732513428, | |
| "learning_rate": 0.0, | |
| "loss": 0.2958, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0023347575354299454, | |
| "eval_loss": 0.2724764943122864, | |
| "eval_runtime": 1241.1547, | |
| "eval_samples_per_second": 7.266, | |
| "eval_steps_per_second": 3.633, | |
| "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": 9555457081344000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |