| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18303843807199513, | |
| "eval_steps": 25, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024405125076266015, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0024405125076266015, | |
| "eval_loss": NaN, | |
| "eval_runtime": 80.3631, | |
| "eval_samples_per_second": 4.293, | |
| "eval_steps_per_second": 2.153, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004881025015253203, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007321537522879805, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009762050030506406, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012202562538133009, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01464307504575961, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017083587553386213, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019524100061012812, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021964612568639415, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.024405125076266018, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026845637583892617, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02928615009151922, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03172666259914582, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.034167175106772425, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.036607687614399025, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.039048200122025624, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.04148871262965223, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04392922513727883, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04636973764490543, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.048810250152532035, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.051250762660158634, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.053691275167785234, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05613178767541183, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05857230018303844, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06101281269066504, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06101281269066504, | |
| "eval_loss": NaN, | |
| "eval_runtime": 80.1089, | |
| "eval_samples_per_second": 4.307, | |
| "eval_steps_per_second": 2.16, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06345332519829164, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001537299608346824, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.06589383770591824, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06833435021354485, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014617486132350343, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.07077486272117145, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014226182617406996, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.07321537522879805, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07565588773642465, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013420201433256689, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07809640024405125, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013007057995042732, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.08053691275167785, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08297742525930446, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012164396139381029, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.08541793776693106, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011736481776669306, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08785845027455766, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09029896278218426, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010871557427476583, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.09273947528981086, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00010436193873653361, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.09517998779743746, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09762050030506407, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.563806126346642e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10006101281269067, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.128442572523417e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.10250152532031727, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.10494203782794387, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.10738255033557047, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.835603860618972e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10982306284319707, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11226357535082367, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.992942004957271e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.11470408785845028, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.579798566743314e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.11714460036607688, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.11958511287370348, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.773817382593008e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.12202562538133008, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.382513867649663e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12202562538133008, | |
| "eval_loss": NaN, | |
| "eval_runtime": 80.3059, | |
| "eval_samples_per_second": 4.296, | |
| "eval_steps_per_second": 2.154, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12446613788895668, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.12690665039658328, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6270039165317605e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1293471629042099, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.264235636489542e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.13178767541183647, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1342281879194631, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5721239031346066e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.1366687004270897, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.244097923843398e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1391092129347163, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.1415497254423429, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6272266318987603e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.14399023794996949, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.339555568810221e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1464307504575961, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14887126296522268, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.808479557110081e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1513117754728493, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.566085541871145e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.1537522879804759, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.1561928004881025, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.129891668217783e-05, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.1586333129957291, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.369221296335006e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.1610738255033557, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1635143380109823, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.030737921409169e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.16595485051860892, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.628304925177318e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.1683953630262355, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.17083587553386212, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3703992880066638e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1732763880414887, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5192246987791981e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.17571690054911532, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.1781574130567419, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.805301908254455e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.18059792556436852, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.517784181422019e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.18303843807199513, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.18303843807199513, | |
| "eval_loss": NaN, | |
| "eval_runtime": 80.075, | |
| "eval_samples_per_second": 4.308, | |
| "eval_steps_per_second": 2.16, | |
| "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": 1.112830925340672e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |