| { | |
| "best_metric": 2.257964849472046, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.8658008658008658, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017316017316017316, | |
| "grad_norm": 2.8213117122650146, | |
| "learning_rate": 1e-05, | |
| "loss": 2.1187, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.017316017316017316, | |
| "eval_loss": 3.7099266052246094, | |
| "eval_runtime": 4.3594, | |
| "eval_samples_per_second": 22.48, | |
| "eval_steps_per_second": 5.735, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03463203463203463, | |
| "grad_norm": 4.985778331756592, | |
| "learning_rate": 2e-05, | |
| "loss": 2.7977, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05194805194805195, | |
| "grad_norm": 4.763190746307373, | |
| "learning_rate": 3e-05, | |
| "loss": 2.7875, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06926406926406926, | |
| "grad_norm": 4.077609062194824, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7441, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08658008658008658, | |
| "grad_norm": 3.072812557220459, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8514, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1038961038961039, | |
| "grad_norm": 2.6697731018066406, | |
| "learning_rate": 6e-05, | |
| "loss": 2.9252, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 2.85693097114563, | |
| "learning_rate": 7e-05, | |
| "loss": 2.6601, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.13852813852813853, | |
| "grad_norm": 3.4699630737304688, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8323, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15584415584415584, | |
| "grad_norm": 3.797606945037842, | |
| "learning_rate": 9e-05, | |
| "loss": 2.8909, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17316017316017315, | |
| "grad_norm": 3.5858542919158936, | |
| "learning_rate": 0.0001, | |
| "loss": 2.822, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19047619047619047, | |
| "grad_norm": 3.080673933029175, | |
| "learning_rate": 9.999071352056675e-05, | |
| "loss": 2.5766, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2077922077922078, | |
| "grad_norm": 4.805807113647461, | |
| "learning_rate": 9.9962857531815e-05, | |
| "loss": 2.7912, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22510822510822512, | |
| "grad_norm": 4.506392002105713, | |
| "learning_rate": 9.99164423811074e-05, | |
| "loss": 2.8573, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 5.713083744049072, | |
| "learning_rate": 9.985148530977767e-05, | |
| "loss": 3.2263, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 1.9132823944091797, | |
| "learning_rate": 9.976801044672608e-05, | |
| "loss": 1.8389, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.27705627705627706, | |
| "grad_norm": 1.8513776063919067, | |
| "learning_rate": 9.966604879945659e-05, | |
| "loss": 2.4264, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2943722943722944, | |
| "grad_norm": 1.6016584634780884, | |
| "learning_rate": 9.954563824255878e-05, | |
| "loss": 2.3631, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3116883116883117, | |
| "grad_norm": 1.684198260307312, | |
| "learning_rate": 9.940682350363912e-05, | |
| "loss": 2.2753, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.329004329004329, | |
| "grad_norm": 1.6534029245376587, | |
| "learning_rate": 9.924965614670629e-05, | |
| "loss": 2.188, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3463203463203463, | |
| "grad_norm": 1.8303340673446655, | |
| "learning_rate": 9.907419455301741e-05, | |
| "loss": 2.036, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.36363636363636365, | |
| "grad_norm": 2.1308131217956543, | |
| "learning_rate": 9.888050389939172e-05, | |
| "loss": 2.352, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 2.047966957092285, | |
| "learning_rate": 9.866865613400008e-05, | |
| "loss": 2.2961, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.39826839826839827, | |
| "grad_norm": 2.1768929958343506, | |
| "learning_rate": 9.843872994963911e-05, | |
| "loss": 2.3702, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.4155844155844156, | |
| "grad_norm": 2.389242172241211, | |
| "learning_rate": 9.819081075450014e-05, | |
| "loss": 2.5131, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.4329004329004329, | |
| "grad_norm": 2.320732831954956, | |
| "learning_rate": 9.792499064044342e-05, | |
| "loss": 2.5102, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45021645021645024, | |
| "grad_norm": 2.5188190937042236, | |
| "learning_rate": 9.764136834878986e-05, | |
| "loss": 2.5501, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4675324675324675, | |
| "grad_norm": 2.676851272583008, | |
| "learning_rate": 9.734004923364257e-05, | |
| "loss": 2.4123, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.48484848484848486, | |
| "grad_norm": 5.181878089904785, | |
| "learning_rate": 9.702114522275216e-05, | |
| "loss": 3.1274, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5021645021645021, | |
| "grad_norm": 1.3181054592132568, | |
| "learning_rate": 9.66847747759402e-05, | |
| "loss": 1.623, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 2.1700284481048584, | |
| "learning_rate": 9.63310628410961e-05, | |
| "loss": 2.2628, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5367965367965368, | |
| "grad_norm": 1.6111098527908325, | |
| "learning_rate": 9.596014080776423e-05, | |
| "loss": 2.071, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5541125541125541, | |
| "grad_norm": 1.5531660318374634, | |
| "learning_rate": 9.557214645833792e-05, | |
| "loss": 2.0633, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 1.5699286460876465, | |
| "learning_rate": 9.516722391687902e-05, | |
| "loss": 2.024, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5887445887445888, | |
| "grad_norm": 1.7361576557159424, | |
| "learning_rate": 9.474552359558166e-05, | |
| "loss": 2.0409, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 1.9074763059616089, | |
| "learning_rate": 9.43072021389003e-05, | |
| "loss": 2.2535, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6233766233766234, | |
| "grad_norm": 1.9367103576660156, | |
| "learning_rate": 9.38524223653626e-05, | |
| "loss": 2.1472, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6406926406926406, | |
| "grad_norm": 2.172595262527466, | |
| "learning_rate": 9.338135320708911e-05, | |
| "loss": 2.3721, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.658008658008658, | |
| "grad_norm": 2.279202699661255, | |
| "learning_rate": 9.289416964704185e-05, | |
| "loss": 2.6207, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6753246753246753, | |
| "grad_norm": 2.3072283267974854, | |
| "learning_rate": 9.239105265402525e-05, | |
| "loss": 2.3583, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6926406926406926, | |
| "grad_norm": 2.4182658195495605, | |
| "learning_rate": 9.187218911546362e-05, | |
| "loss": 2.3313, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.70995670995671, | |
| "grad_norm": 2.541595220565796, | |
| "learning_rate": 9.133777176798013e-05, | |
| "loss": 2.381, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7272727272727273, | |
| "grad_norm": 4.249802112579346, | |
| "learning_rate": 9.078799912580304e-05, | |
| "loss": 2.3142, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7445887445887446, | |
| "grad_norm": 0.995394229888916, | |
| "learning_rate": 9.022307540702576e-05, | |
| "loss": 1.7486, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 1.733182430267334, | |
| "learning_rate": 8.964321045774807e-05, | |
| "loss": 2.057, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 1.6964753866195679, | |
| "learning_rate": 8.904861967412703e-05, | |
| "loss": 2.0244, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7965367965367965, | |
| "grad_norm": 1.5640254020690918, | |
| "learning_rate": 8.843952392236594e-05, | |
| "loss": 1.8624, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8138528138528138, | |
| "grad_norm": 1.5645256042480469, | |
| "learning_rate": 8.781614945667169e-05, | |
| "loss": 2.1798, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8311688311688312, | |
| "grad_norm": 1.4937459230422974, | |
| "learning_rate": 8.717872783521047e-05, | |
| "loss": 2.0126, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8484848484848485, | |
| "grad_norm": 1.6373777389526367, | |
| "learning_rate": 8.65274958340934e-05, | |
| "loss": 1.879, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8658008658008658, | |
| "grad_norm": 1.8210711479187012, | |
| "learning_rate": 8.586269535942385e-05, | |
| "loss": 2.1558, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8658008658008658, | |
| "eval_loss": 2.257964849472046, | |
| "eval_runtime": 4.389, | |
| "eval_samples_per_second": 22.329, | |
| "eval_steps_per_second": 5.696, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 173, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.07184013033472e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |