| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.050057510927076145, | |
| "eval_steps": 50, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014722797331492984, | |
| "grad_norm": 0.26644960045814514, | |
| "learning_rate": 7.499999999999999e-06, | |
| "loss": 0.296, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014722797331492984, | |
| "eval_loss": 0.4772031009197235, | |
| "eval_runtime": 847.2862, | |
| "eval_samples_per_second": 2.7, | |
| "eval_steps_per_second": 1.35, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029445594662985968, | |
| "grad_norm": 0.4351513385772705, | |
| "learning_rate": 1.4999999999999999e-05, | |
| "loss": 0.408, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004416839199447895, | |
| "grad_norm": 0.3042258024215698, | |
| "learning_rate": 2.2499999999999998e-05, | |
| "loss": 0.393, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0058891189325971935, | |
| "grad_norm": 0.3164433538913727, | |
| "learning_rate": 2.9999999999999997e-05, | |
| "loss": 0.409, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007361398665746492, | |
| "grad_norm": 0.37835752964019775, | |
| "learning_rate": 3.75e-05, | |
| "loss": 0.2635, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00883367839889579, | |
| "grad_norm": 0.22859500348567963, | |
| "learning_rate": 4.4999999999999996e-05, | |
| "loss": 0.2615, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010305958132045089, | |
| "grad_norm": 0.37722575664520264, | |
| "learning_rate": 5.2499999999999995e-05, | |
| "loss": 0.296, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011778237865194387, | |
| "grad_norm": 0.8506933450698853, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 0.2655, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013250517598343685, | |
| "grad_norm": 0.45279720425605774, | |
| "learning_rate": 6.75e-05, | |
| "loss": 0.259, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014722797331492983, | |
| "grad_norm": 0.18526464700698853, | |
| "learning_rate": 7.5e-05, | |
| "loss": 0.2053, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.016195077064642283, | |
| "grad_norm": 0.20497167110443115, | |
| "learning_rate": 8.25e-05, | |
| "loss": 0.1554, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01766735679779158, | |
| "grad_norm": 0.14627239108085632, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 0.1306, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.01913963653094088, | |
| "grad_norm": 0.240932434797287, | |
| "learning_rate": 9.75e-05, | |
| "loss": 0.1564, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.020611916264090178, | |
| "grad_norm": 0.3040555715560913, | |
| "learning_rate": 0.00010499999999999999, | |
| "loss": 0.1677, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.022084195997239476, | |
| "grad_norm": 0.4959651231765747, | |
| "learning_rate": 0.0001125, | |
| "loss": 0.3867, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.023556475730388774, | |
| "grad_norm": 0.20291835069656372, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 0.2207, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.025028755463538072, | |
| "grad_norm": 0.16518566012382507, | |
| "learning_rate": 0.00012749999999999998, | |
| "loss": 0.1309, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02650103519668737, | |
| "grad_norm": 0.18677189946174622, | |
| "learning_rate": 0.000135, | |
| "loss": 0.181, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.02797331492983667, | |
| "grad_norm": 0.1576640009880066, | |
| "learning_rate": 0.0001425, | |
| "loss": 0.1562, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.029445594662985967, | |
| "grad_norm": 0.19666102528572083, | |
| "learning_rate": 0.00015, | |
| "loss": 0.2439, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030917874396135265, | |
| "grad_norm": 0.12512515485286713, | |
| "learning_rate": 0.00014998857713672935, | |
| "loss": 0.144, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03239015412928457, | |
| "grad_norm": 0.1219751164317131, | |
| "learning_rate": 0.00014995431202643217, | |
| "loss": 0.1047, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.033862433862433865, | |
| "grad_norm": 0.1390693038702011, | |
| "learning_rate": 0.000149897215106593, | |
| "loss": 0.1022, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03533471359558316, | |
| "grad_norm": 0.19809921085834503, | |
| "learning_rate": 0.0001498173037694868, | |
| "loss": 0.24, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03680699332873246, | |
| "grad_norm": 0.17452572286128998, | |
| "learning_rate": 0.0001497146023568809, | |
| "loss": 0.2497, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03827927306188176, | |
| "grad_norm": 0.10941721498966217, | |
| "learning_rate": 0.00014958914215262048, | |
| "loss": 0.0914, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03975155279503106, | |
| "grad_norm": 0.12793776392936707, | |
| "learning_rate": 0.00014944096137309914, | |
| "loss": 0.114, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.041223832528180356, | |
| "grad_norm": 0.14925755560398102, | |
| "learning_rate": 0.00014927010515561776, | |
| "loss": 0.1931, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.042696112261329654, | |
| "grad_norm": 0.12749770283699036, | |
| "learning_rate": 0.00014907662554463532, | |
| "loss": 0.1342, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04416839199447895, | |
| "grad_norm": 0.12666098773479462, | |
| "learning_rate": 0.0001488605814759156, | |
| "loss": 0.1404, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04564067172762825, | |
| "grad_norm": 0.12451935559511185, | |
| "learning_rate": 0.00014862203875857477, | |
| "loss": 0.1297, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04711295146077755, | |
| "grad_norm": 0.12354013323783875, | |
| "learning_rate": 0.0001483610700550354, | |
| "loss": 0.0667, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.048585231193926846, | |
| "grad_norm": 0.11861127614974976, | |
| "learning_rate": 0.00014807775485889264, | |
| "loss": 0.1057, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.050057510927076145, | |
| "grad_norm": 0.11489235609769821, | |
| "learning_rate": 0.0001477721794706997, | |
| "loss": 0.0717, | |
| "step": 34 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 17, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.597635405563822e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |