| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 33750, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 3.210815906524658, | |
| "learning_rate": 4.925925925925926e-05, | |
| "loss": 0.4315, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 8.126620292663574, | |
| "learning_rate": 4.851851851851852e-05, | |
| "loss": 0.2862, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 4.665143013000488, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.237, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 2.0566887855529785, | |
| "learning_rate": 4.703703703703704e-05, | |
| "loss": 0.2251, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 7.968118667602539, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.2239, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 1.2121827602386475, | |
| "learning_rate": 4.555555555555556e-05, | |
| "loss": 0.2203, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": 3.395099401473999, | |
| "learning_rate": 4.481481481481482e-05, | |
| "loss": 0.2111, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 1.9526039361953735, | |
| "learning_rate": 4.4074074074074076e-05, | |
| "loss": 0.193, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 3.2926955223083496, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.1853, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 2.8749849796295166, | |
| "learning_rate": 4.259259259259259e-05, | |
| "loss": 0.1675, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.4888888888888889, | |
| "grad_norm": 6.5106706619262695, | |
| "learning_rate": 4.185185185185185e-05, | |
| "loss": 0.1889, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 1.893872618675232, | |
| "learning_rate": 4.111111111111111e-05, | |
| "loss": 0.2002, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.5777777777777777, | |
| "grad_norm": 4.822785377502441, | |
| "learning_rate": 4.0370370370370374e-05, | |
| "loss": 0.1802, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 2.410318374633789, | |
| "learning_rate": 3.962962962962963e-05, | |
| "loss": 0.1578, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 7.345259189605713, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.1668, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 2.6905734539031982, | |
| "learning_rate": 3.814814814814815e-05, | |
| "loss": 0.1726, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.7555555555555555, | |
| "grad_norm": 7.399478912353516, | |
| "learning_rate": 3.740740740740741e-05, | |
| "loss": 0.1586, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 1.8845775127410889, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.1629, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.8444444444444444, | |
| "grad_norm": 3.4357192516326904, | |
| "learning_rate": 3.592592592592593e-05, | |
| "loss": 0.1674, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 1.8075140714645386, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 0.1671, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": 2.545607089996338, | |
| "learning_rate": 3.444444444444445e-05, | |
| "loss": 0.1595, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 2.33050799369812, | |
| "learning_rate": 3.3703703703703706e-05, | |
| "loss": 0.1655, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.0222222222222221, | |
| "grad_norm": 1.9340065717697144, | |
| "learning_rate": 3.2962962962962964e-05, | |
| "loss": 0.1349, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 1.3230476379394531, | |
| "learning_rate": 3.222222222222223e-05, | |
| "loss": 0.1069, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 4.054622650146484, | |
| "learning_rate": 3.148148148148148e-05, | |
| "loss": 0.1098, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 4.885370254516602, | |
| "learning_rate": 3.074074074074074e-05, | |
| "loss": 0.1162, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "grad_norm": 3.5849854946136475, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1077, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 9.765403747558594, | |
| "learning_rate": 2.925925925925926e-05, | |
| "loss": 0.1181, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.2888888888888888, | |
| "grad_norm": 3.879992961883545, | |
| "learning_rate": 2.851851851851852e-05, | |
| "loss": 0.1011, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 2.2347288131713867, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1175, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.3777777777777778, | |
| "grad_norm": 7.474192142486572, | |
| "learning_rate": 2.7037037037037037e-05, | |
| "loss": 0.1073, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 4.1693291664123535, | |
| "learning_rate": 2.6296296296296296e-05, | |
| "loss": 0.0995, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.4666666666666668, | |
| "grad_norm": 1.8383170366287231, | |
| "learning_rate": 2.5555555555555554e-05, | |
| "loss": 0.1145, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 0.694262683391571, | |
| "learning_rate": 2.4814814814814816e-05, | |
| "loss": 0.115, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.5555555555555556, | |
| "grad_norm": 0.9633584022521973, | |
| "learning_rate": 2.4074074074074074e-05, | |
| "loss": 0.1024, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 2.0199620723724365, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.1011, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.6444444444444444, | |
| "grad_norm": 1.8132920265197754, | |
| "learning_rate": 2.2592592592592594e-05, | |
| "loss": 0.1041, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 8.3416748046875, | |
| "learning_rate": 2.1851851851851852e-05, | |
| "loss": 0.1144, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.7333333333333334, | |
| "grad_norm": 1.4581434726715088, | |
| "learning_rate": 2.111111111111111e-05, | |
| "loss": 0.0955, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 3.9014599323272705, | |
| "learning_rate": 2.037037037037037e-05, | |
| "loss": 0.104, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.8222222222222222, | |
| "grad_norm": 2.070230007171631, | |
| "learning_rate": 1.962962962962963e-05, | |
| "loss": 0.0995, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 0.8812291026115417, | |
| "learning_rate": 1.888888888888889e-05, | |
| "loss": 0.0982, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.911111111111111, | |
| "grad_norm": 1.1036711931228638, | |
| "learning_rate": 1.814814814814815e-05, | |
| "loss": 0.0987, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 0.6822977066040039, | |
| "learning_rate": 1.740740740740741e-05, | |
| "loss": 0.101, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 4.314443111419678, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0979, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 3.5247573852539062, | |
| "learning_rate": 1.5925925925925926e-05, | |
| "loss": 0.0733, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.088888888888889, | |
| "grad_norm": 0.6801110506057739, | |
| "learning_rate": 1.5185185185185186e-05, | |
| "loss": 0.0651, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 4.516416072845459, | |
| "learning_rate": 1.4444444444444444e-05, | |
| "loss": 0.0765, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.1777777777777776, | |
| "grad_norm": 1.9308606386184692, | |
| "learning_rate": 1.3703703703703704e-05, | |
| "loss": 0.0707, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 1.1442885398864746, | |
| "learning_rate": 1.2962962962962962e-05, | |
| "loss": 0.0617, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 2.2666666666666666, | |
| "grad_norm": 5.30832576751709, | |
| "learning_rate": 1.2222222222222222e-05, | |
| "loss": 0.0693, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 2.311111111111111, | |
| "grad_norm": 0.5708422660827637, | |
| "learning_rate": 1.1481481481481482e-05, | |
| "loss": 0.0697, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 2.3555555555555556, | |
| "grad_norm": 0.680268406867981, | |
| "learning_rate": 1.074074074074074e-05, | |
| "loss": 0.066, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 0.72934889793396, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0644, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 2.4444444444444446, | |
| "grad_norm": 4.663362503051758, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.0667, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 1.3758256435394287, | |
| "learning_rate": 8.518518518518519e-06, | |
| "loss": 0.0575, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 2.533333333333333, | |
| "grad_norm": 0.8022651672363281, | |
| "learning_rate": 7.777777777777777e-06, | |
| "loss": 0.0621, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 2.5777777777777775, | |
| "grad_norm": 1.576392412185669, | |
| "learning_rate": 7.0370370370370375e-06, | |
| "loss": 0.0586, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 2.6222222222222222, | |
| "grad_norm": 1.166567087173462, | |
| "learning_rate": 6.296296296296296e-06, | |
| "loss": 0.0662, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 2.4423012733459473, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0645, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.7111111111111112, | |
| "grad_norm": 3.1122899055480957, | |
| "learning_rate": 4.814814814814815e-06, | |
| "loss": 0.0642, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 2.7555555555555555, | |
| "grad_norm": 3.2840280532836914, | |
| "learning_rate": 4.074074074074075e-06, | |
| "loss": 0.0617, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.6285051703453064, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.0566, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 3.462080240249634, | |
| "learning_rate": 2.5925925925925925e-06, | |
| "loss": 0.0614, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 2.888888888888889, | |
| "grad_norm": 2.2216219902038574, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 0.0647, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 2.9333333333333336, | |
| "grad_norm": 1.6926839351654053, | |
| "learning_rate": 1.1111111111111112e-06, | |
| "loss": 0.0611, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 2.977777777777778, | |
| "grad_norm": 4.723779678344727, | |
| "learning_rate": 3.703703703703704e-07, | |
| "loss": 0.0597, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 33750, | |
| "total_flos": 4446488701440000.0, | |
| "train_loss": 0.12363309427897136, | |
| "train_runtime": 1375.441, | |
| "train_samples_per_second": 196.301, | |
| "train_steps_per_second": 24.538 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 33750, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4446488701440000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |