| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.09528346831824679, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0019056693663649356, | |
| "eval_loss": 3.0111310482025146, | |
| "eval_runtime": 139.5262, | |
| "eval_samples_per_second": 6.336, | |
| "eval_steps_per_second": 0.796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005717008099094807, | |
| "grad_norm": 1.745223045349121, | |
| "learning_rate": 3e-05, | |
| "loss": 2.8529, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009528346831824679, | |
| "eval_loss": 2.849209785461426, | |
| "eval_runtime": 140.6511, | |
| "eval_samples_per_second": 6.285, | |
| "eval_steps_per_second": 0.789, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011434016198189614, | |
| "grad_norm": 1.5631052255630493, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8163, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01715102429728442, | |
| "grad_norm": 1.3446643352508545, | |
| "learning_rate": 9e-05, | |
| "loss": 2.5454, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.019056693663649357, | |
| "eval_loss": 2.5639851093292236, | |
| "eval_runtime": 140.6263, | |
| "eval_samples_per_second": 6.286, | |
| "eval_steps_per_second": 0.789, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022868032396379228, | |
| "grad_norm": 1.6127707958221436, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.5243, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.028585040495474036, | |
| "grad_norm": 1.2866557836532593, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3552, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.028585040495474036, | |
| "eval_loss": 2.4209542274475098, | |
| "eval_runtime": 140.5703, | |
| "eval_samples_per_second": 6.289, | |
| "eval_steps_per_second": 0.79, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03430204859456884, | |
| "grad_norm": 1.7916969060897827, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.6218, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.038113387327298714, | |
| "eval_loss": 2.3375890254974365, | |
| "eval_runtime": 140.5851, | |
| "eval_samples_per_second": 6.288, | |
| "eval_steps_per_second": 0.79, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04001905669366365, | |
| "grad_norm": 1.3049689531326294, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 2.2512, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.045736064792758456, | |
| "grad_norm": 1.2573634386062622, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 2.2554, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04764173415912339, | |
| "eval_loss": 2.2932698726654053, | |
| "eval_runtime": 140.5269, | |
| "eval_samples_per_second": 6.291, | |
| "eval_steps_per_second": 0.79, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05145307289185326, | |
| "grad_norm": 1.093232274055481, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 2.1642, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05717008099094807, | |
| "grad_norm": 1.1265302896499634, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2761, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05717008099094807, | |
| "eval_loss": 2.271261215209961, | |
| "eval_runtime": 140.6344, | |
| "eval_samples_per_second": 6.286, | |
| "eval_steps_per_second": 0.789, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06288708909004288, | |
| "grad_norm": 3.7034900188446045, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 2.2029, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06669842782277274, | |
| "eval_loss": 2.2650718688964844, | |
| "eval_runtime": 140.6225, | |
| "eval_samples_per_second": 6.286, | |
| "eval_steps_per_second": 0.789, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06860409718913768, | |
| "grad_norm": 1.4284329414367676, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 2.2225, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07432110528823249, | |
| "grad_norm": 1.1168383359909058, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 2.108, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07622677465459743, | |
| "eval_loss": 2.249340534210205, | |
| "eval_runtime": 140.5814, | |
| "eval_samples_per_second": 6.288, | |
| "eval_steps_per_second": 0.79, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0800381133873273, | |
| "grad_norm": 0.9819179773330688, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.1547, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0857551214864221, | |
| "grad_norm": 0.888201892375946, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1645, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0857551214864221, | |
| "eval_loss": 2.2474822998046875, | |
| "eval_runtime": 140.5849, | |
| "eval_samples_per_second": 6.288, | |
| "eval_steps_per_second": 0.79, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.09147212958551691, | |
| "grad_norm": 1.5101863145828247, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 2.1671, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09528346831824679, | |
| "eval_loss": 2.2469546794891357, | |
| "eval_runtime": 140.6128, | |
| "eval_samples_per_second": 6.287, | |
| "eval_steps_per_second": 0.789, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.508513578745856e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |