| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.20036315822428152, |
| "eval_steps": 500, |
| "global_step": 400, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005009078955607038, |
| "grad_norm": 3.8452577590942383, |
| "learning_rate": 0.0001, |
| "loss": 3.7141, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.010018157911214076, |
| "grad_norm": 1.3136709928512573, |
| "learning_rate": 0.0002, |
| "loss": 2.5276, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.015027236866821113, |
| "grad_norm": 1.7088837623596191, |
| "learning_rate": 0.000199658449300667, |
| "loss": 1.5061, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.020036315822428152, |
| "grad_norm": 1.5081887245178223, |
| "learning_rate": 0.00019863613034027224, |
| "loss": 1.3611, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.02504539477803519, |
| "grad_norm": 1.4680248498916626, |
| "learning_rate": 0.00019694002659393305, |
| "loss": 1.2824, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.030054473733642225, |
| "grad_norm": 1.4349300861358643, |
| "learning_rate": 0.00019458172417006347, |
| "loss": 1.2862, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.03506355268924927, |
| "grad_norm": 1.3822752237319946, |
| "learning_rate": 0.00019157733266550575, |
| "loss": 1.2418, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.040072631644856305, |
| "grad_norm": 1.3204342126846313, |
| "learning_rate": 0.0001879473751206489, |
| "loss": 1.1863, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.04508171060046334, |
| "grad_norm": 1.6619811058044434, |
| "learning_rate": 0.00018371664782625287, |
| "loss": 1.292, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.05009078955607038, |
| "grad_norm": 1.519755482673645, |
| "learning_rate": 0.00017891405093963938, |
| "loss": 1.3015, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.05509986851167741, |
| "grad_norm": 1.11312997341156, |
| "learning_rate": 0.00017357239106731317, |
| "loss": 0.9784, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.06010894746728445, |
| "grad_norm": 1.171500563621521, |
| "learning_rate": 0.00016772815716257412, |
| "loss": 1.0728, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.0651180264228915, |
| "grad_norm": 1.573570728302002, |
| "learning_rate": 0.0001614212712689668, |
| "loss": 1.0383, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.07012710537849853, |
| "grad_norm": 1.2490291595458984, |
| "learning_rate": 0.00015469481581224272, |
| "loss": 0.9686, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.07513618433410557, |
| "grad_norm": 1.2631878852844238, |
| "learning_rate": 0.00014759473930370736, |
| "loss": 0.8221, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.08014526328971261, |
| "grad_norm": 1.264460802078247, |
| "learning_rate": 0.00014016954246529696, |
| "loss": 1.0505, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.08515434224531965, |
| "grad_norm": 1.6487361192703247, |
| "learning_rate": 0.00013246994692046836, |
| "loss": 0.9273, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.09016342120092669, |
| "grad_norm": 1.2811675071716309, |
| "learning_rate": 0.00012454854871407994, |
| "loss": 1.0738, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.09517250015653372, |
| "grad_norm": 1.3107404708862305, |
| "learning_rate": 0.00011645945902807341, |
| "loss": 1.0617, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.10018157911214076, |
| "grad_norm": 1.3991544246673584, |
| "learning_rate": 0.00010825793454723325, |
| "loss": 1.0279, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1051906580677478, |
| "grad_norm": 0.982639491558075, |
| "learning_rate": 0.0001, |
| "loss": 0.6177, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.11019973702335482, |
| "grad_norm": 1.3960201740264893, |
| "learning_rate": 9.174206545276677e-05, |
| "loss": 1.1537, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.11520881597896186, |
| "grad_norm": 1.1508264541625977, |
| "learning_rate": 8.35405409719266e-05, |
| "loss": 1.0193, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.1202178949345689, |
| "grad_norm": 1.4218165874481201, |
| "learning_rate": 7.54514512859201e-05, |
| "loss": 0.9139, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.12522697389017595, |
| "grad_norm": 1.4765474796295166, |
| "learning_rate": 6.753005307953167e-05, |
| "loss": 1.0649, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.130236052845783, |
| "grad_norm": 1.854028344154358, |
| "learning_rate": 5.983045753470308e-05, |
| "loss": 1.0795, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.13524513180139003, |
| "grad_norm": 1.1793019771575928, |
| "learning_rate": 5.240526069629265e-05, |
| "loss": 1.0884, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.14025421075699707, |
| "grad_norm": 1.3754643201828003, |
| "learning_rate": 4.530518418775733e-05, |
| "loss": 1.0449, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.1452632897126041, |
| "grad_norm": 1.337937831878662, |
| "learning_rate": 3.857872873103322e-05, |
| "loss": 0.7611, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.15027236866821114, |
| "grad_norm": 1.337849497795105, |
| "learning_rate": 3.227184283742591e-05, |
| "loss": 1.1993, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.15528144762381818, |
| "grad_norm": 1.6689127683639526, |
| "learning_rate": 2.6427608932686843e-05, |
| "loss": 1.0456, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.16029052657942522, |
| "grad_norm": 1.2203370332717896, |
| "learning_rate": 2.1085949060360654e-05, |
| "loss": 0.869, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.16529960553503226, |
| "grad_norm": 1.5624113082885742, |
| "learning_rate": 1.6283352173747145e-05, |
| "loss": 0.9677, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.1703086844906393, |
| "grad_norm": 1.4291284084320068, |
| "learning_rate": 1.2052624879351104e-05, |
| "loss": 0.9613, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.17531776344624633, |
| "grad_norm": 1.324217677116394, |
| "learning_rate": 8.422667334494249e-06, |
| "loss": 0.8151, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.18032684240185337, |
| "grad_norm": 1.0875211954116821, |
| "learning_rate": 5.418275829936537e-06, |
| "loss": 0.8445, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.1853359213574604, |
| "grad_norm": 1.5346405506134033, |
| "learning_rate": 3.059973406066963e-06, |
| "loss": 0.8916, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.19034500031306745, |
| "grad_norm": 1.3770543336868286, |
| "learning_rate": 1.3638696597277679e-06, |
| "loss": 0.9675, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.19535407926867449, |
| "grad_norm": 1.5972645282745361, |
| "learning_rate": 3.415506993330153e-07, |
| "loss": 0.7615, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.20036315822428152, |
| "grad_norm": 1.0311360359191895, |
| "learning_rate": 0.0, |
| "loss": 0.7726, |
| "step": 400 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 400, |
| "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": 7.30567126488384e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
