| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.10084033613445378, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016806722689075631, | |
| "grad_norm": 0.08711077272891998, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7892, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033613445378151263, | |
| "grad_norm": 0.12688124179840088, | |
| "learning_rate": 8e-05, | |
| "loss": 0.9025, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005042016806722689, | |
| "grad_norm": 0.10088784247636795, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7134, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0067226890756302525, | |
| "grad_norm": 0.09177786111831665, | |
| "learning_rate": 0.00016, | |
| "loss": 0.927, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008403361344537815, | |
| "grad_norm": 0.2383689433336258, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8999, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010084033613445379, | |
| "grad_norm": 0.07735294103622437, | |
| "learning_rate": 0.00019636363636363636, | |
| "loss": 0.8429, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011764705882352941, | |
| "grad_norm": 0.07536331564188004, | |
| "learning_rate": 0.00019272727272727274, | |
| "loss": 0.7763, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013445378151260505, | |
| "grad_norm": 0.08141479641199112, | |
| "learning_rate": 0.0001890909090909091, | |
| "loss": 0.5322, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.015126050420168067, | |
| "grad_norm": 0.0736273005604744, | |
| "learning_rate": 0.00018545454545454545, | |
| "loss": 0.6342, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01680672268907563, | |
| "grad_norm": 0.10946282744407654, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.7587, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018487394957983194, | |
| "grad_norm": 0.07774144411087036, | |
| "learning_rate": 0.0001781818181818182, | |
| "loss": 0.6685, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.020168067226890758, | |
| "grad_norm": 0.07681110501289368, | |
| "learning_rate": 0.00017454545454545454, | |
| "loss": 1.064, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021848739495798318, | |
| "grad_norm": 0.08137353509664536, | |
| "learning_rate": 0.0001709090909090909, | |
| "loss": 0.8278, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023529411764705882, | |
| "grad_norm": 0.15623211860656738, | |
| "learning_rate": 0.00016727272727272728, | |
| "loss": 0.6985, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.025210084033613446, | |
| "grad_norm": 0.10167036205530167, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 0.8868, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02689075630252101, | |
| "grad_norm": 0.1013818234205246, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9126, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02857142857142857, | |
| "grad_norm": 0.09055998921394348, | |
| "learning_rate": 0.00015636363636363637, | |
| "loss": 0.7888, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.030252100840336135, | |
| "grad_norm": 0.16094405949115753, | |
| "learning_rate": 0.00015272727272727275, | |
| "loss": 0.6225, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.031932773109243695, | |
| "grad_norm": 0.21245548129081726, | |
| "learning_rate": 0.0001490909090909091, | |
| "loss": 0.6745, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03361344537815126, | |
| "grad_norm": 0.08682460337877274, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 0.7252, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03529411764705882, | |
| "grad_norm": 0.08345898985862732, | |
| "learning_rate": 0.00014181818181818184, | |
| "loss": 0.638, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03697478991596639, | |
| "grad_norm": 0.08165189623832703, | |
| "learning_rate": 0.0001381818181818182, | |
| "loss": 0.9751, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03865546218487395, | |
| "grad_norm": 0.08062303811311722, | |
| "learning_rate": 0.00013454545454545455, | |
| "loss": 0.7559, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.040336134453781515, | |
| "grad_norm": 0.07231509685516357, | |
| "learning_rate": 0.00013090909090909093, | |
| "loss": 0.71, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04201680672268908, | |
| "grad_norm": 0.07577697187662125, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 0.7186, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.043697478991596636, | |
| "grad_norm": 0.07562875002622604, | |
| "learning_rate": 0.00012363636363636364, | |
| "loss": 0.9232, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0453781512605042, | |
| "grad_norm": 0.07023375481367111, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8472, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.047058823529411764, | |
| "grad_norm": 0.07514394819736481, | |
| "learning_rate": 0.00011636363636363636, | |
| "loss": 0.7765, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04873949579831933, | |
| "grad_norm": 0.08253440260887146, | |
| "learning_rate": 0.00011272727272727272, | |
| "loss": 0.6163, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05042016806722689, | |
| "grad_norm": 0.09420851618051529, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 0.6294, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.052100840336134456, | |
| "grad_norm": 0.07622350007295609, | |
| "learning_rate": 0.00010545454545454545, | |
| "loss": 0.7741, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.05378151260504202, | |
| "grad_norm": 0.08414219319820404, | |
| "learning_rate": 0.00010181818181818181, | |
| "loss": 0.7156, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.05546218487394958, | |
| "grad_norm": 0.07866919785737991, | |
| "learning_rate": 9.818181818181818e-05, | |
| "loss": 0.7736, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05714285714285714, | |
| "grad_norm": 0.07867816835641861, | |
| "learning_rate": 9.454545454545455e-05, | |
| "loss": 0.7042, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.07410237193107605, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.8446, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06050420168067227, | |
| "grad_norm": 0.07834600657224655, | |
| "learning_rate": 8.727272727272727e-05, | |
| "loss": 0.8873, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06218487394957983, | |
| "grad_norm": 0.08074888586997986, | |
| "learning_rate": 8.363636363636364e-05, | |
| "loss": 0.6879, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06386554621848739, | |
| "grad_norm": 0.06010926514863968, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6882, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06554621848739496, | |
| "grad_norm": 0.08766958117485046, | |
| "learning_rate": 7.636363636363637e-05, | |
| "loss": 0.6037, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06722689075630252, | |
| "grad_norm": 0.07735378295183182, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.6251, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06890756302521009, | |
| "grad_norm": 0.0956479161977768, | |
| "learning_rate": 6.90909090909091e-05, | |
| "loss": 1.0099, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07058823529411765, | |
| "grad_norm": 0.07726597785949707, | |
| "learning_rate": 6.545454545454546e-05, | |
| "loss": 0.5449, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07226890756302522, | |
| "grad_norm": 0.07963621616363525, | |
| "learning_rate": 6.181818181818182e-05, | |
| "loss": 0.6568, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07394957983193277, | |
| "grad_norm": 0.08890356868505478, | |
| "learning_rate": 5.818181818181818e-05, | |
| "loss": 0.7226, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07563025210084033, | |
| "grad_norm": 0.07577082514762878, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.7658, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0773109243697479, | |
| "grad_norm": 0.07142199575901031, | |
| "learning_rate": 5.090909090909091e-05, | |
| "loss": 0.63, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07899159663865546, | |
| "grad_norm": 0.0648496150970459, | |
| "learning_rate": 4.7272727272727275e-05, | |
| "loss": 0.6635, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.08067226890756303, | |
| "grad_norm": 0.11062151193618774, | |
| "learning_rate": 4.3636363636363636e-05, | |
| "loss": 0.5822, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08235294117647059, | |
| "grad_norm": 0.08142093569040298, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9608, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08403361344537816, | |
| "grad_norm": 0.08923624455928802, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.7617, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08571428571428572, | |
| "grad_norm": 0.07603711634874344, | |
| "learning_rate": 3.272727272727273e-05, | |
| "loss": 0.4793, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.08739495798319327, | |
| "grad_norm": 0.08750972151756287, | |
| "learning_rate": 2.909090909090909e-05, | |
| "loss": 0.8154, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.08907563025210084, | |
| "grad_norm": 0.07799336314201355, | |
| "learning_rate": 2.5454545454545454e-05, | |
| "loss": 0.7218, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.0907563025210084, | |
| "grad_norm": 0.07668763399124146, | |
| "learning_rate": 2.1818181818181818e-05, | |
| "loss": 0.6844, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.09243697478991597, | |
| "grad_norm": 0.07868485897779465, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.7515, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 0.06420107930898666, | |
| "learning_rate": 1.4545454545454545e-05, | |
| "loss": 0.5804, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.0957983193277311, | |
| "grad_norm": 0.07881864905357361, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 0.6701, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.09747899159663866, | |
| "grad_norm": 0.07414459437131882, | |
| "learning_rate": 7.272727272727272e-06, | |
| "loss": 0.6471, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.09915966386554621, | |
| "grad_norm": 0.08740859478712082, | |
| "learning_rate": 3.636363636363636e-06, | |
| "loss": 0.699, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.10084033613445378, | |
| "grad_norm": 0.0815616026520729, | |
| "learning_rate": 0.0, | |
| "loss": 0.8564, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 2.136603104667648e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |