| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.17101325352714836, | |
| "eval_steps": 10, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017101325352714834, | |
| "eval_loss": 3.379563808441162, | |
| "eval_runtime": 4.6539, | |
| "eval_samples_per_second": 105.934, | |
| "eval_steps_per_second": 26.645, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008550662676357419, | |
| "grad_norm": 16.06174659729004, | |
| "learning_rate": 0.0001, | |
| "loss": 3.091, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017101325352714837, | |
| "grad_norm": 30.746688842773438, | |
| "learning_rate": 0.0002, | |
| "loss": 3.2285, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017101325352714837, | |
| "eval_loss": 3.323244094848633, | |
| "eval_runtime": 4.6253, | |
| "eval_samples_per_second": 106.589, | |
| "eval_steps_per_second": 26.809, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.025651988029072252, | |
| "grad_norm": 54.02665710449219, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 3.2701, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.034202650705429674, | |
| "grad_norm": 34.668582916259766, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 3.2074, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.034202650705429674, | |
| "eval_loss": 3.245879888534546, | |
| "eval_runtime": 4.8152, | |
| "eval_samples_per_second": 102.383, | |
| "eval_steps_per_second": 25.752, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04275331338178709, | |
| "grad_norm": 50.34535598754883, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 3.5141, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.051303976058144504, | |
| "grad_norm": 22.065715789794922, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 3.1801, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.051303976058144504, | |
| "eval_loss": 3.2354209423065186, | |
| "eval_runtime": 4.7495, | |
| "eval_samples_per_second": 103.8, | |
| "eval_steps_per_second": 26.108, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.059854638734501926, | |
| "grad_norm": 16.38636016845703, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 3.193, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06840530141085935, | |
| "grad_norm": 31.518808364868164, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.3996, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06840530141085935, | |
| "eval_loss": 3.22153902053833, | |
| "eval_runtime": 4.3761, | |
| "eval_samples_per_second": 112.657, | |
| "eval_steps_per_second": 28.336, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07695596408721676, | |
| "grad_norm": 27.541791915893555, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 3.2613, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08550662676357418, | |
| "grad_norm": 43.12064743041992, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 3.5703, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08550662676357418, | |
| "eval_loss": 3.2112386226654053, | |
| "eval_runtime": 4.6985, | |
| "eval_samples_per_second": 104.927, | |
| "eval_steps_per_second": 26.391, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0940572894399316, | |
| "grad_norm": 24.017574310302734, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0906, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.10260795211628901, | |
| "grad_norm": 72.96064758300781, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 3.1746, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.10260795211628901, | |
| "eval_loss": 3.197736978530884, | |
| "eval_runtime": 4.499, | |
| "eval_samples_per_second": 109.58, | |
| "eval_steps_per_second": 27.562, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11115861479264642, | |
| "grad_norm": 37.74872970581055, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 3.1812, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.11970927746900385, | |
| "grad_norm": 22.35642433166504, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 3.1637, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.11970927746900385, | |
| "eval_loss": 3.1739985942840576, | |
| "eval_runtime": 4.7892, | |
| "eval_samples_per_second": 102.941, | |
| "eval_steps_per_second": 25.892, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12825994014536127, | |
| "grad_norm": 37.37099075317383, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 3.4387, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1368106028217187, | |
| "grad_norm": 14.69621467590332, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 3.0516, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1368106028217187, | |
| "eval_loss": 3.148390054702759, | |
| "eval_runtime": 4.685, | |
| "eval_samples_per_second": 105.229, | |
| "eval_steps_per_second": 26.467, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1453612654980761, | |
| "grad_norm": 32.74094009399414, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 3.1578, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.15391192817443353, | |
| "grad_norm": 22.851362228393555, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 3.1172, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.15391192817443353, | |
| "eval_loss": 3.1573593616485596, | |
| "eval_runtime": 4.7749, | |
| "eval_samples_per_second": 103.249, | |
| "eval_steps_per_second": 25.969, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16246259085079093, | |
| "grad_norm": 15.831418991088867, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 3.3129, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.17101325352714836, | |
| "grad_norm": 58.72257614135742, | |
| "learning_rate": 0.0, | |
| "loss": 3.4377, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17101325352714836, | |
| "eval_loss": 3.1490554809570312, | |
| "eval_runtime": 4.6256, | |
| "eval_samples_per_second": 106.582, | |
| "eval_steps_per_second": 26.808, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2549851317338112.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |