| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 13, |
| "global_step": 66, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.045454545454545456, |
| "grad_norm": 0.26570865511894226, |
| "learning_rate": 0.0, |
| "loss": 1.0991, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.09090909090909091, |
| "grad_norm": 0.19788296520709991, |
| "learning_rate": 0.0001, |
| "loss": 1.1858, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.13636363636363635, |
| "grad_norm": 0.2018503099679947, |
| "learning_rate": 0.0002, |
| "loss": 1.4282, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 0.14019116759300232, |
| "learning_rate": 0.00019989159105846555, |
| "loss": 1.0461, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.22727272727272727, |
| "grad_norm": 0.0761001780629158, |
| "learning_rate": 0.00019956662540049773, |
| "loss": 1.1584, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2727272727272727, |
| "grad_norm": 0.06310273706912994, |
| "learning_rate": 0.0001990258858968303, |
| "loss": 1.2249, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.3181818181818182, |
| "grad_norm": 0.07300414144992828, |
| "learning_rate": 0.00019827067523629075, |
| "loss": 0.8899, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 0.06310679018497467, |
| "learning_rate": 0.00019730281278750898, |
| "loss": 1.1826, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.4090909090909091, |
| "grad_norm": 0.06386806070804596, |
| "learning_rate": 0.0001961246302158988, |
| "loss": 1.1252, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.45454545454545453, |
| "grad_norm": 0.06900643557310104, |
| "learning_rate": 0.00019473896586647186, |
| "loss": 1.0732, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 0.05214522033929825, |
| "learning_rate": 0.00019314915792601581, |
| "loss": 1.1494, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 0.035811204463243484, |
| "learning_rate": 0.00019135903638110993, |
| "loss": 0.7997, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.5909090909090909, |
| "grad_norm": 0.044281817972660065, |
| "learning_rate": 0.00018937291379135196, |
| "loss": 1.1821, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "grad_norm": 0.04433455318212509, |
| "learning_rate": 0.0001871955749000245, |
| "loss": 1.1196, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6363636363636364, |
| "eval_loss": 1.0, |
| "eval_runtime": 1.6972, |
| "eval_samples_per_second": 0.589, |
| "eval_steps_per_second": 0.589, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.6818181818181818, |
| "grad_norm": 0.04366498067975044, |
| "learning_rate": 0.0001848322651072291, |
| "loss": 1.1431, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 0.04259055480360985, |
| "learning_rate": 0.00018228867783325804, |
| "loss": 1.2317, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.7727272727272727, |
| "grad_norm": 0.03771774098277092, |
| "learning_rate": 0.00017957094080264634, |
| "loss": 1.1204, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.8181818181818182, |
| "grad_norm": 0.03440351411700249, |
| "learning_rate": 0.00017668560128194635, |
| "loss": 0.9883, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.8636363636363636, |
| "grad_norm": 0.03425208106637001, |
| "learning_rate": 0.00017363961030678927, |
| "loss": 1.0967, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 0.02954299934208393, |
| "learning_rate": 0.00017044030593623167, |
| "loss": 0.6606, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9545454545454546, |
| "grad_norm": 0.3488457202911377, |
| "learning_rate": 0.0001670953955747281, |
| "loss": 0.9198, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.032931141555309296, |
| "learning_rate": 0.00016361293740431904, |
| "loss": 0.9204, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.0454545454545454, |
| "grad_norm": 0.03185806795954704, |
| "learning_rate": 0.00016000132097176422, |
| "loss": 0.7996, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.0909090909090908, |
| "grad_norm": 0.03138045594096184, |
| "learning_rate": 0.00015626924697738993, |
| "loss": 0.927, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.1363636363636362, |
| "grad_norm": 0.03675857186317444, |
| "learning_rate": 0.0001524257063143398, |
| "loss": 1.1428, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.1818181818181819, |
| "grad_norm": 0.027697354555130005, |
| "learning_rate": 0.0001484799584087254, |
| "loss": 0.8362, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.2272727272727273, |
| "grad_norm": 0.028406554833054543, |
| "learning_rate": 0.00014444150891285807, |
| "loss": 0.9871, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.2272727272727273, |
| "eval_loss": 0.9453125, |
| "eval_runtime": 1.699, |
| "eval_samples_per_second": 0.589, |
| "eval_steps_per_second": 0.589, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.2727272727272727, |
| "grad_norm": 0.026174945756793022, |
| "learning_rate": 0.0001403200868052998, |
| "loss": 1.0741, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.3181818181818181, |
| "grad_norm": 0.030307767912745476, |
| "learning_rate": 0.0001361256209529016, |
| "loss": 0.7305, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 0.028039664030075073, |
| "learning_rate": 0.00013186821619129378, |
| "loss": 1.0569, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.4090909090909092, |
| "grad_norm": 0.02829521894454956, |
| "learning_rate": 0.00012755812898145155, |
| "loss": 1.0015, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.4545454545454546, |
| "grad_norm": 0.02784855291247368, |
| "learning_rate": 0.00012320574270098254, |
| "loss": 0.9619, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 0.024387067183852196, |
| "learning_rate": 0.0001188215426296605, |
| "loss": 1.0562, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.5454545454545454, |
| "grad_norm": 0.0228856410831213, |
| "learning_rate": 0.00011441609068946764, |
| "loss": 0.731, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.5909090909090908, |
| "grad_norm": 0.024063974618911743, |
| "learning_rate": 0.00011000000000000002, |
| "loss": 1.1125, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.6363636363636362, |
| "grad_norm": 0.026135141029953957, |
| "learning_rate": 0.0001055839093105324, |
| "loss": 1.0291, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.6818181818181817, |
| "grad_norm": 0.02611403912305832, |
| "learning_rate": 0.00010117845737033956, |
| "loss": 1.0682, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.7272727272727273, |
| "grad_norm": 0.025955649092793465, |
| "learning_rate": 9.679425729901746e-05, |
| "loss": 1.1604, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.7727272727272727, |
| "grad_norm": 0.024920133873820305, |
| "learning_rate": 9.244187101854847e-05, |
| "loss": 1.0432, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "grad_norm": 0.023373816162347794, |
| "learning_rate": 8.813178380870625e-05, |
| "loss": 0.921, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.8181818181818183, |
| "eval_loss": 0.921875, |
| "eval_runtime": 1.7126, |
| "eval_samples_per_second": 0.584, |
| "eval_steps_per_second": 0.584, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.8636363636363638, |
| "grad_norm": 0.025230776518583298, |
| "learning_rate": 8.38743790470984e-05, |
| "loss": 1.0305, |
| "step": 41 |
| }, |
| { |
| "epoch": 1.9090909090909092, |
| "grad_norm": 0.02200430817902088, |
| "learning_rate": 7.96799131947002e-05, |
| "loss": 0.5916, |
| "step": 42 |
| }, |
| { |
| "epoch": 1.9545454545454546, |
| "grad_norm": 0.021784311160445213, |
| "learning_rate": 7.555849108714192e-05, |
| "loss": 0.8511, |
| "step": 43 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.022025559097528458, |
| "learning_rate": 7.152004159127463e-05, |
| "loss": 0.8629, |
| "step": 44 |
| }, |
| { |
| "epoch": 2.0454545454545454, |
| "grad_norm": 0.0236300490796566, |
| "learning_rate": 6.757429368566022e-05, |
| "loss": 0.7417, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.090909090909091, |
| "grad_norm": 0.024307960644364357, |
| "learning_rate": 6.373075302261006e-05, |
| "loss": 0.8741, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.1363636363636362, |
| "grad_norm": 0.02563675306737423, |
| "learning_rate": 5.9998679028235824e-05, |
| "loss": 1.0909, |
| "step": 47 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "grad_norm": 0.023581454530358315, |
| "learning_rate": 5.6387062595681006e-05, |
| "loss": 0.785, |
| "step": 48 |
| }, |
| { |
| "epoch": 2.227272727272727, |
| "grad_norm": 0.0233762226998806, |
| "learning_rate": 5.290460442527192e-05, |
| "loss": 0.9403, |
| "step": 49 |
| }, |
| { |
| "epoch": 2.2727272727272725, |
| "grad_norm": 0.023589802905917168, |
| "learning_rate": 4.955969406376835e-05, |
| "loss": 1.0319, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.3181818181818183, |
| "grad_norm": 0.023750334978103638, |
| "learning_rate": 4.6360389693210735e-05, |
| "loss": 0.6851, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.3636363636363638, |
| "grad_norm": 0.022339332848787308, |
| "learning_rate": 4.33143987180537e-05, |
| "loss": 1.0183, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.409090909090909, |
| "grad_norm": 0.02258870005607605, |
| "learning_rate": 4.042905919735367e-05, |
| "loss": 0.9631, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.409090909090909, |
| "eval_loss": 0.91015625, |
| "eval_runtime": 1.7022, |
| "eval_samples_per_second": 0.587, |
| "eval_steps_per_second": 0.587, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.4545454545454546, |
| "grad_norm": 0.025404134765267372, |
| "learning_rate": 3.771132216674197e-05, |
| "loss": 0.9232, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 0.021336553618311882, |
| "learning_rate": 3.516773489277092e-05, |
| "loss": 1.0229, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 0.016827255487442017, |
| "learning_rate": 3.2804425099975525e-05, |
| "loss": 0.707, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.590909090909091, |
| "grad_norm": 0.022356828674674034, |
| "learning_rate": 3.062708620864806e-05, |
| "loss": 1.0881, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.6363636363636362, |
| "grad_norm": 0.023688841611146927, |
| "learning_rate": 2.8640963618890103e-05, |
| "loss": 0.999, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.6818181818181817, |
| "grad_norm": 0.022186871618032455, |
| "learning_rate": 2.6850842073984196e-05, |
| "loss": 1.0435, |
| "step": 59 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 0.023007292300462723, |
| "learning_rate": 2.5261034133528138e-05, |
| "loss": 1.1348, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.7727272727272725, |
| "grad_norm": 0.023376451805233955, |
| "learning_rate": 2.387536978410121e-05, |
| "loss": 1.0161, |
| "step": 61 |
| }, |
| { |
| "epoch": 2.8181818181818183, |
| "grad_norm": 0.02313663810491562, |
| "learning_rate": 2.2697187212491044e-05, |
| "loss": 0.8971, |
| "step": 62 |
| }, |
| { |
| "epoch": 2.8636363636363638, |
| "grad_norm": 0.023053674027323723, |
| "learning_rate": 2.1729324763709264e-05, |
| "loss": 1.0046, |
| "step": 63 |
| }, |
| { |
| "epoch": 2.909090909090909, |
| "grad_norm": 0.021076248958706856, |
| "learning_rate": 2.0974114103169712e-05, |
| "loss": 0.5725, |
| "step": 64 |
| }, |
| { |
| "epoch": 2.9545454545454546, |
| "grad_norm": 0.021139593794941902, |
| "learning_rate": 2.043337459950229e-05, |
| "loss": 0.8326, |
| "step": 65 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.021683219820261, |
| "learning_rate": 2.0108408941534486e-05, |
| "loss": 0.8434, |
| "step": 66 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.90234375, |
| "eval_runtime": 1.6966, |
| "eval_samples_per_second": 0.589, |
| "eval_steps_per_second": 0.589, |
| "step": 66 |
| } |
| ], |
| "logging_steps": 1.0, |
| "max_steps": 66, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 0, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.291814797437829e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
