| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06379585326953748, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008506113769271664, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008506113769271664, | |
| "eval_loss": NaN, | |
| "eval_runtime": 247.3677, | |
| "eval_samples_per_second": 4.002, | |
| "eval_steps_per_second": 2.001, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017012227538543328, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004253056884635832, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005103668261562998, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005954279638490165, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006804891015417331, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007655502392344498, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008506113769271665, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00935672514619883, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011057947900053162, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.01190855927698033, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013609782030834662, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.014460393407761828, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.015311004784688996, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01616161616161616, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01701222753854333, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017862838915470493, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01956406166932483, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.020414673046251993, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02126528442317916, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02126528442317916, | |
| "eval_loss": NaN, | |
| "eval_runtime": 247.9824, | |
| "eval_samples_per_second": 3.992, | |
| "eval_steps_per_second": 1.996, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.022115895800106325, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.022966507177033493, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02381711855396066, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.024667729930887825, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.025518341307814992, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.02636895268474216, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.027219564061669324, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.028070175438596492, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.028920786815523656, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.029771398192450824, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03062200956937799, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03147262094630516, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03232323232323232, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03317384370015949, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03402445507708666, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03487506645401382, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03572567783094099, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03657628920786816, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03742690058479532, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03827751196172249, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03912812333864966, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03997873471557682, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.040829346092503986, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04167995746943115, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04253056884635832, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04253056884635832, | |
| "eval_loss": NaN, | |
| "eval_runtime": 248.2887, | |
| "eval_samples_per_second": 3.987, | |
| "eval_steps_per_second": 1.994, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.043381180223285486, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.04423179160021265, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04508240297713982, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.045933014354066985, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.04678362573099415, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04763423710792132, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.048484848484848485, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.04933545986177565, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.05018607123870282, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.051036682615629984, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05188729399255715, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05273790536948432, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.053588516746411484, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05443912812333865, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05528973950026582, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05699096225412015, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.05784157363104731, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.05869218500797448, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.05954279638490165, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06039340776182881, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.06124401913875598, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06209463051568315, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.06294524189261032, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06379585326953748, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06379585326953748, | |
| "eval_loss": NaN, | |
| "eval_runtime": 248.2077, | |
| "eval_samples_per_second": 3.989, | |
| "eval_steps_per_second": 1.994, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1513752134352896e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |