| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.28498147620404674, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005699629524080934, | |
| "grad_norm": 19.25, | |
| "learning_rate": 9.982896237172178e-06, | |
| "loss": 2.0698, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011399259048161869, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 9.963892056252377e-06, | |
| "loss": 1.5026, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017098888572242805, | |
| "grad_norm": 6.5, | |
| "learning_rate": 9.944887875332574e-06, | |
| "loss": 1.4607, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.022798518096323737, | |
| "grad_norm": 6.5625, | |
| "learning_rate": 9.925883694412771e-06, | |
| "loss": 1.3855, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.028498147620404674, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 9.90687951349297e-06, | |
| "loss": 1.4154, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03419777714448561, | |
| "grad_norm": 5.90625, | |
| "learning_rate": 9.887875332573167e-06, | |
| "loss": 1.3327, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.039897406668566546, | |
| "grad_norm": 12.9375, | |
| "learning_rate": 9.868871151653364e-06, | |
| "loss": 1.3797, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.045597036192647475, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 9.849866970733563e-06, | |
| "loss": 1.361, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05129666571672841, | |
| "grad_norm": 7.0, | |
| "learning_rate": 9.83086278981376e-06, | |
| "loss": 1.4097, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05699629524080935, | |
| "grad_norm": 6.46875, | |
| "learning_rate": 9.811858608893958e-06, | |
| "loss": 1.3784, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06269592476489028, | |
| "grad_norm": 6.09375, | |
| "learning_rate": 9.792854427974155e-06, | |
| "loss": 1.3886, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06839555428897122, | |
| "grad_norm": 7.0625, | |
| "learning_rate": 9.773850247054353e-06, | |
| "loss": 1.2982, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07409518381305215, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 9.75484606613455e-06, | |
| "loss": 1.3887, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.07979481333713309, | |
| "grad_norm": 5.46875, | |
| "learning_rate": 9.735841885214748e-06, | |
| "loss": 1.3336, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.08549444286121402, | |
| "grad_norm": 6.78125, | |
| "learning_rate": 9.716837704294946e-06, | |
| "loss": 1.3523, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09119407238529495, | |
| "grad_norm": 7.96875, | |
| "learning_rate": 9.697833523375144e-06, | |
| "loss": 1.3483, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09689370190937589, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 9.678829342455342e-06, | |
| "loss": 1.3502, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.10259333143345682, | |
| "grad_norm": 7.0, | |
| "learning_rate": 9.65982516153554e-06, | |
| "loss": 1.3553, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.10829296095753776, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 9.640820980615736e-06, | |
| "loss": 1.338, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1139925904816187, | |
| "grad_norm": 7.3125, | |
| "learning_rate": 9.621816799695934e-06, | |
| "loss": 1.3868, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11969222000569962, | |
| "grad_norm": 6.53125, | |
| "learning_rate": 9.602812618776132e-06, | |
| "loss": 1.3996, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.12539184952978055, | |
| "grad_norm": 7.8125, | |
| "learning_rate": 9.58380843785633e-06, | |
| "loss": 1.3638, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.1310914790538615, | |
| "grad_norm": 6.90625, | |
| "learning_rate": 9.564804256936528e-06, | |
| "loss": 1.2893, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.13679110857794244, | |
| "grad_norm": 6.9375, | |
| "learning_rate": 9.545800076016724e-06, | |
| "loss": 1.3408, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.14249073810202337, | |
| "grad_norm": 6.4375, | |
| "learning_rate": 9.526795895096922e-06, | |
| "loss": 1.3522, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.1481903676261043, | |
| "grad_norm": 6.59375, | |
| "learning_rate": 9.50779171417712e-06, | |
| "loss": 1.3595, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.15388999715018523, | |
| "grad_norm": 7.125, | |
| "learning_rate": 9.488787533257318e-06, | |
| "loss": 1.381, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.15958962667426618, | |
| "grad_norm": 7.1875, | |
| "learning_rate": 9.469783352337516e-06, | |
| "loss": 1.3109, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.1652892561983471, | |
| "grad_norm": 7.09375, | |
| "learning_rate": 9.450779171417712e-06, | |
| "loss": 1.3793, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.17098888572242804, | |
| "grad_norm": 7.125, | |
| "learning_rate": 9.43177499049791e-06, | |
| "loss": 1.3373, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.17668851524650897, | |
| "grad_norm": 6.5625, | |
| "learning_rate": 9.412770809578108e-06, | |
| "loss": 1.3474, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.1823881447705899, | |
| "grad_norm": 7.03125, | |
| "learning_rate": 9.393766628658306e-06, | |
| "loss": 1.3076, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.18808777429467086, | |
| "grad_norm": 7.71875, | |
| "learning_rate": 9.374762447738504e-06, | |
| "loss": 1.2929, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.19378740381875179, | |
| "grad_norm": 6.8125, | |
| "learning_rate": 9.3557582668187e-06, | |
| "loss": 1.3652, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.19948703334283271, | |
| "grad_norm": 7.15625, | |
| "learning_rate": 9.336754085898898e-06, | |
| "loss": 1.3535, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.20518666286691364, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 9.317749904979096e-06, | |
| "loss": 1.3388, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.21088629239099457, | |
| "grad_norm": 7.6875, | |
| "learning_rate": 9.298745724059294e-06, | |
| "loss": 1.3083, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.21658592191507553, | |
| "grad_norm": 7.125, | |
| "learning_rate": 9.279741543139492e-06, | |
| "loss": 1.3409, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.22228555143915646, | |
| "grad_norm": 6.78125, | |
| "learning_rate": 9.26073736221969e-06, | |
| "loss": 1.3149, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.2279851809632374, | |
| "grad_norm": 6.3125, | |
| "learning_rate": 9.241733181299886e-06, | |
| "loss": 1.3525, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.23368481048731832, | |
| "grad_norm": 7.34375, | |
| "learning_rate": 9.222729000380084e-06, | |
| "loss": 1.3343, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.23938444001139925, | |
| "grad_norm": 6.875, | |
| "learning_rate": 9.203724819460282e-06, | |
| "loss": 1.3098, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.2450840695354802, | |
| "grad_norm": 5.8125, | |
| "learning_rate": 9.18472063854048e-06, | |
| "loss": 1.2878, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.2507836990595611, | |
| "grad_norm": 6.0625, | |
| "learning_rate": 9.165716457620676e-06, | |
| "loss": 1.2681, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.2564833285836421, | |
| "grad_norm": 7.09375, | |
| "learning_rate": 9.146712276700876e-06, | |
| "loss": 1.2974, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.262182958107723, | |
| "grad_norm": 6.96875, | |
| "learning_rate": 9.127708095781072e-06, | |
| "loss": 1.3047, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.26788258763180395, | |
| "grad_norm": 7.40625, | |
| "learning_rate": 9.10870391486127e-06, | |
| "loss": 1.2063, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.2735822171558849, | |
| "grad_norm": 7.59375, | |
| "learning_rate": 9.089699733941468e-06, | |
| "loss": 1.3046, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.2792818466799658, | |
| "grad_norm": 5.9375, | |
| "learning_rate": 9.070695553021666e-06, | |
| "loss": 1.2633, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.28498147620404674, | |
| "grad_norm": 7.3125, | |
| "learning_rate": 9.051691372101862e-06, | |
| "loss": 1.3394, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5262, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1649856397312e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |