| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1701041888156496, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008505209440782479, | |
| "eval_loss": 1.785892128944397, | |
| "eval_runtime": 17.3247, | |
| "eval_samples_per_second": 28.572, | |
| "eval_steps_per_second": 14.315, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00850520944078248, | |
| "grad_norm": 1.3187812566757202, | |
| "learning_rate": 0.0002, | |
| "loss": 6.8373, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01701041888156496, | |
| "grad_norm": 2.7719953060150146, | |
| "learning_rate": 0.0002, | |
| "loss": 6.5746, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02551562832234744, | |
| "grad_norm": 1.4612891674041748, | |
| "learning_rate": 0.0002, | |
| "loss": 6.7459, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03402083776312992, | |
| "grad_norm": 1.6617029905319214, | |
| "learning_rate": 0.0002, | |
| "loss": 6.2728, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0425260472039124, | |
| "grad_norm": 1.557134747505188, | |
| "learning_rate": 0.0002, | |
| "loss": 6.3201, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0425260472039124, | |
| "eval_loss": 1.5907841920852661, | |
| "eval_runtime": 17.2481, | |
| "eval_samples_per_second": 28.699, | |
| "eval_steps_per_second": 14.378, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05103125664469488, | |
| "grad_norm": 1.6395306587219238, | |
| "learning_rate": 0.0002, | |
| "loss": 6.604, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05953646608547736, | |
| "grad_norm": 1.8522754907608032, | |
| "learning_rate": 0.0002, | |
| "loss": 6.2886, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06804167552625984, | |
| "grad_norm": 1.2497164011001587, | |
| "learning_rate": 0.0002, | |
| "loss": 6.1894, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07654688496704232, | |
| "grad_norm": 2.200613498687744, | |
| "learning_rate": 0.0002, | |
| "loss": 6.2773, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0850520944078248, | |
| "grad_norm": 1.8427073955535889, | |
| "learning_rate": 0.0002, | |
| "loss": 6.392, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0850520944078248, | |
| "eval_loss": 1.5734424591064453, | |
| "eval_runtime": 17.2504, | |
| "eval_samples_per_second": 28.695, | |
| "eval_steps_per_second": 14.377, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.09355730384860728, | |
| "grad_norm": 1.8528062105178833, | |
| "learning_rate": 0.0002, | |
| "loss": 6.2375, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.10206251328938976, | |
| "grad_norm": 2.0559117794036865, | |
| "learning_rate": 0.0002, | |
| "loss": 6.3323, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.11056772273017224, | |
| "grad_norm": 2.75404691696167, | |
| "learning_rate": 0.0002, | |
| "loss": 6.3663, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.11907293217095472, | |
| "grad_norm": 1.2870985269546509, | |
| "learning_rate": 0.0002, | |
| "loss": 6.2035, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1275781416117372, | |
| "grad_norm": 1.0647329092025757, | |
| "learning_rate": 0.0002, | |
| "loss": 6.1095, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1275781416117372, | |
| "eval_loss": 1.5614224672317505, | |
| "eval_runtime": 17.2171, | |
| "eval_samples_per_second": 28.75, | |
| "eval_steps_per_second": 14.404, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.13608335105251967, | |
| "grad_norm": 2.079286813735962, | |
| "learning_rate": 0.0002, | |
| "loss": 6.5172, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.14458856049330215, | |
| "grad_norm": 1.3619401454925537, | |
| "learning_rate": 0.0002, | |
| "loss": 6.367, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.15309376993408463, | |
| "grad_norm": 0.9493538737297058, | |
| "learning_rate": 0.0002, | |
| "loss": 6.197, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1615989793748671, | |
| "grad_norm": 1.0273698568344116, | |
| "learning_rate": 0.0002, | |
| "loss": 6.6096, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1701041888156496, | |
| "grad_norm": 1.0309791564941406, | |
| "learning_rate": 0.0002, | |
| "loss": 6.1175, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.1701041888156496, | |
| "eval_loss": 1.5528790950775146, | |
| "eval_runtime": 17.2234, | |
| "eval_samples_per_second": 28.74, | |
| "eval_steps_per_second": 14.399, | |
| "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": 2.2696397264388096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |