| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9977827050997783, | |
| "eval_steps": 500, | |
| "global_step": 225, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004434589800443459, | |
| "grad_norm": 1.91265869140625, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 2.8127, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022172949002217297, | |
| "grad_norm": 1.5314122438430786, | |
| "learning_rate": 0.0002173913043478261, | |
| "loss": 2.7241, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04434589800443459, | |
| "grad_norm": 0.6431057453155518, | |
| "learning_rate": 0.0004347826086956522, | |
| "loss": 2.2423, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06651884700665188, | |
| "grad_norm": 0.5257381200790405, | |
| "learning_rate": 0.0006521739130434783, | |
| "loss": 1.9505, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08869179600886919, | |
| "grad_norm": 0.37703999876976013, | |
| "learning_rate": 0.0008695652173913044, | |
| "loss": 1.7881, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11086474501108648, | |
| "grad_norm": 0.30256885290145874, | |
| "learning_rate": 0.0009900990099009901, | |
| "loss": 1.7031, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.13303769401330376, | |
| "grad_norm": 0.3443244993686676, | |
| "learning_rate": 0.0009653465346534653, | |
| "loss": 1.6352, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.15521064301552107, | |
| "grad_norm": 0.369827538728714, | |
| "learning_rate": 0.0009405940594059406, | |
| "loss": 1.5746, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.17738359201773837, | |
| "grad_norm": 0.231527641415596, | |
| "learning_rate": 0.0009158415841584159, | |
| "loss": 1.5409, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.19955654101995565, | |
| "grad_norm": 0.22827404737472534, | |
| "learning_rate": 0.0008910891089108911, | |
| "loss": 1.5187, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.22172949002217296, | |
| "grad_norm": 0.2396710067987442, | |
| "learning_rate": 0.0008663366336633663, | |
| "loss": 1.5128, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.24390243902439024, | |
| "grad_norm": 0.20095600187778473, | |
| "learning_rate": 0.0008415841584158416, | |
| "loss": 1.4848, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2660753880266075, | |
| "grad_norm": 0.28900983929634094, | |
| "learning_rate": 0.0008168316831683168, | |
| "loss": 1.4962, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.28824833702882485, | |
| "grad_norm": 0.25716254115104675, | |
| "learning_rate": 0.0007920792079207921, | |
| "loss": 1.4789, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.31042128603104213, | |
| "grad_norm": 0.252340167760849, | |
| "learning_rate": 0.0007673267326732674, | |
| "loss": 1.458, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3325942350332594, | |
| "grad_norm": 0.20464155077934265, | |
| "learning_rate": 0.0007425742574257426, | |
| "loss": 1.4558, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.35476718403547675, | |
| "grad_norm": 0.23394732177257538, | |
| "learning_rate": 0.0007178217821782178, | |
| "loss": 1.4562, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.376940133037694, | |
| "grad_norm": 0.2164139449596405, | |
| "learning_rate": 0.000693069306930693, | |
| "loss": 1.4338, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3991130820399113, | |
| "grad_norm": 0.215862438082695, | |
| "learning_rate": 0.0006683168316831684, | |
| "loss": 1.4287, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4212860310421286, | |
| "grad_norm": 0.20270515978336334, | |
| "learning_rate": 0.0006435643564356436, | |
| "loss": 1.4226, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.4434589800443459, | |
| "grad_norm": 0.20255711674690247, | |
| "learning_rate": 0.0006188118811881188, | |
| "loss": 1.4314, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4656319290465632, | |
| "grad_norm": 0.20747065544128418, | |
| "learning_rate": 0.000594059405940594, | |
| "loss": 1.4194, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 0.2104884535074234, | |
| "learning_rate": 0.0005693069306930693, | |
| "loss": 1.4106, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.5099778270509978, | |
| "grad_norm": 0.21514882147312164, | |
| "learning_rate": 0.0005445544554455446, | |
| "loss": 1.42, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.532150776053215, | |
| "grad_norm": 0.20466424524784088, | |
| "learning_rate": 0.0005198019801980198, | |
| "loss": 1.3937, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5543237250554324, | |
| "grad_norm": 0.2181282341480255, | |
| "learning_rate": 0.0004950495049504951, | |
| "loss": 1.3972, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5764966740576497, | |
| "grad_norm": 0.22615699470043182, | |
| "learning_rate": 0.0004702970297029703, | |
| "loss": 1.3882, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5986696230598669, | |
| "grad_norm": 0.1967965066432953, | |
| "learning_rate": 0.00044554455445544556, | |
| "loss": 1.388, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.6208425720620843, | |
| "grad_norm": 0.2030034065246582, | |
| "learning_rate": 0.0004207920792079208, | |
| "loss": 1.4048, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.6430155210643016, | |
| "grad_norm": 0.2136310189962387, | |
| "learning_rate": 0.00039603960396039607, | |
| "loss": 1.3918, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.6651884700665188, | |
| "grad_norm": 0.22149060666561127, | |
| "learning_rate": 0.0003712871287128713, | |
| "loss": 1.4023, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6873614190687362, | |
| "grad_norm": 0.2130667269229889, | |
| "learning_rate": 0.0003465346534653465, | |
| "loss": 1.3933, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.7095343680709535, | |
| "grad_norm": 0.19920696318149567, | |
| "learning_rate": 0.0003217821782178218, | |
| "loss": 1.3815, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.7317073170731707, | |
| "grad_norm": 0.20453611016273499, | |
| "learning_rate": 0.000297029702970297, | |
| "loss": 1.3648, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.753880266075388, | |
| "grad_norm": 0.21325863897800446, | |
| "learning_rate": 0.0002722772277227723, | |
| "loss": 1.3773, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7760532150776053, | |
| "grad_norm": 0.2014823704957962, | |
| "learning_rate": 0.00024752475247524753, | |
| "loss": 1.3881, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.7982261640798226, | |
| "grad_norm": 0.20359407365322113, | |
| "learning_rate": 0.00022277227722772278, | |
| "loss": 1.3826, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.8203991130820399, | |
| "grad_norm": 0.21738748252391815, | |
| "learning_rate": 0.00019801980198019803, | |
| "loss": 1.3705, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8425720620842572, | |
| "grad_norm": 0.1990172564983368, | |
| "learning_rate": 0.00017326732673267326, | |
| "loss": 1.3693, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.8647450110864745, | |
| "grad_norm": 0.2007543295621872, | |
| "learning_rate": 0.0001485148514851485, | |
| "loss": 1.3575, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.8869179600886918, | |
| "grad_norm": 0.5149243474006653, | |
| "learning_rate": 0.00012376237623762376, | |
| "loss": 1.374, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.9090909090909091, | |
| "grad_norm": 0.2131042778491974, | |
| "learning_rate": 9.900990099009902e-05, | |
| "loss": 1.3636, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.9312638580931264, | |
| "grad_norm": 0.19097404181957245, | |
| "learning_rate": 7.425742574257426e-05, | |
| "loss": 1.3489, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9534368070953437, | |
| "grad_norm": 0.19905418157577515, | |
| "learning_rate": 4.950495049504951e-05, | |
| "loss": 1.3442, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 0.19617854058742523, | |
| "learning_rate": 2.4752475247524754e-05, | |
| "loss": 1.3721, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9977827050997783, | |
| "grad_norm": 0.20064575970172882, | |
| "learning_rate": 0.0, | |
| "loss": 1.3767, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9977827050997783, | |
| "eval_loss": 1.7732421159744263, | |
| "eval_runtime": 0.5415, | |
| "eval_samples_per_second": 1.847, | |
| "eval_steps_per_second": 1.847, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9977827050997783, | |
| "step": 225, | |
| "total_flos": 3.3259687694984806e+17, | |
| "train_loss": 1.4963340536753336, | |
| "train_runtime": 725.2803, | |
| "train_samples_per_second": 9.934, | |
| "train_steps_per_second": 0.31 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 225, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.3259687694984806e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |