| { |
| "best_global_step": 60, |
| "best_metric": 2.1111679077148438, |
| "best_model_checkpoint": "/tmp/checkpoints_/job_2d7db242-d10c-4b68-8580-8faf9983d2ac/checkpoint-60", |
| "epoch": 3.0, |
| "eval_steps": 50, |
| "global_step": 60, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "grad_norm": 5.003835201263428, |
| "learning_rate": 0.0, |
| "loss": 3.3008522987365723, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 4.970128536224365, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 3.225693464279175, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 4.844517707824707, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 3.3512721061706543, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 5.368833541870117, |
| "learning_rate": 1.2e-05, |
| "loss": 3.379887342453003, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 4.891224384307861, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 3.259934663772583, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 4.492045879364014, |
| "learning_rate": 2e-05, |
| "loss": 3.375720500946045, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 4.809245586395264, |
| "learning_rate": 1.963636363636364e-05, |
| "loss": 3.172975778579712, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 4.000991344451904, |
| "learning_rate": 1.9272727272727275e-05, |
| "loss": 3.133239507675171, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 4.314571857452393, |
| "learning_rate": 1.8909090909090912e-05, |
| "loss": 2.960566520690918, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 4.391575336456299, |
| "learning_rate": 1.8545454545454545e-05, |
| "loss": 3.036698579788208, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 3.654188394546509, |
| "learning_rate": 1.8181818181818182e-05, |
| "loss": 3.0613582134246826, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 3.5731828212738037, |
| "learning_rate": 1.781818181818182e-05, |
| "loss": 2.8887860774993896, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 3.337536573410034, |
| "learning_rate": 1.7454545454545456e-05, |
| "loss": 2.870251178741455, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 4.155342102050781, |
| "learning_rate": 1.7090909090909092e-05, |
| "loss": 2.988539695739746, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 3.459912061691284, |
| "learning_rate": 1.672727272727273e-05, |
| "loss": 2.8767173290252686, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 3.0474016666412354, |
| "learning_rate": 1.6363636363636366e-05, |
| "loss": 2.7056357860565186, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 3.38972544670105, |
| "learning_rate": 1.6000000000000003e-05, |
| "loss": 2.8308351039886475, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 3.3401777744293213, |
| "learning_rate": 1.563636363636364e-05, |
| "loss": 2.798548698425293, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 3.516348361968994, |
| "learning_rate": 1.5272727272727276e-05, |
| "loss": 2.745471954345703, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.335920572280884, |
| "learning_rate": 1.4909090909090911e-05, |
| "loss": 2.5934133529663086, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.05, |
| "grad_norm": 3.27337908744812, |
| "learning_rate": 1.4545454545454546e-05, |
| "loss": 2.7366790771484375, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.1, |
| "grad_norm": 3.8487720489501953, |
| "learning_rate": 1.4181818181818183e-05, |
| "loss": 2.634737968444824, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.15, |
| "grad_norm": 3.5459773540496826, |
| "learning_rate": 1.381818181818182e-05, |
| "loss": 2.505260467529297, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 2.969346523284912, |
| "learning_rate": 1.3454545454545455e-05, |
| "loss": 2.641937017440796, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 4.165552139282227, |
| "learning_rate": 1.3090909090909092e-05, |
| "loss": 2.4418344497680664, |
| "step": 25 |
| }, |
| { |
| "epoch": 1.3, |
| "grad_norm": 3.034208059310913, |
| "learning_rate": 1.2727272727272728e-05, |
| "loss": 2.608135223388672, |
| "step": 26 |
| }, |
| { |
| "epoch": 1.35, |
| "grad_norm": 2.993718147277832, |
| "learning_rate": 1.2363636363636364e-05, |
| "loss": 2.5002670288085938, |
| "step": 27 |
| }, |
| { |
| "epoch": 1.4, |
| "grad_norm": 2.8328919410705566, |
| "learning_rate": 1.2e-05, |
| "loss": 2.4381470680236816, |
| "step": 28 |
| }, |
| { |
| "epoch": 1.45, |
| "grad_norm": 3.087843179702759, |
| "learning_rate": 1.1636363636363637e-05, |
| "loss": 2.4134974479675293, |
| "step": 29 |
| }, |
| { |
| "epoch": 1.5, |
| "grad_norm": 3.460454225540161, |
| "learning_rate": 1.1272727272727272e-05, |
| "loss": 2.3297386169433594, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.55, |
| "grad_norm": 3.5020861625671387, |
| "learning_rate": 1.0909090909090909e-05, |
| "loss": 2.4366676807403564, |
| "step": 31 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 2.866708755493164, |
| "learning_rate": 1.0545454545454546e-05, |
| "loss": 2.3938283920288086, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.65, |
| "grad_norm": 3.988553047180176, |
| "learning_rate": 1.0181818181818182e-05, |
| "loss": 2.3989124298095703, |
| "step": 33 |
| }, |
| { |
| "epoch": 1.7, |
| "grad_norm": 3.4233789443969727, |
| "learning_rate": 9.81818181818182e-06, |
| "loss": 2.447577953338623, |
| "step": 34 |
| }, |
| { |
| "epoch": 1.75, |
| "grad_norm": 4.505123615264893, |
| "learning_rate": 9.454545454545456e-06, |
| "loss": 2.6081345081329346, |
| "step": 35 |
| }, |
| { |
| "epoch": 1.8, |
| "grad_norm": 3.3041152954101562, |
| "learning_rate": 9.090909090909091e-06, |
| "loss": 2.1873340606689453, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.85, |
| "grad_norm": 3.5472681522369385, |
| "learning_rate": 8.727272727272728e-06, |
| "loss": 2.2423746585845947, |
| "step": 37 |
| }, |
| { |
| "epoch": 1.9, |
| "grad_norm": 3.41754150390625, |
| "learning_rate": 8.363636363636365e-06, |
| "loss": 2.329379081726074, |
| "step": 38 |
| }, |
| { |
| "epoch": 1.95, |
| "grad_norm": 2.987565755844116, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 2.4018678665161133, |
| "step": 39 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 3.6949684619903564, |
| "learning_rate": 7.636363636363638e-06, |
| "loss": 2.2103075981140137, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.05, |
| "grad_norm": 2.9741289615631104, |
| "learning_rate": 7.272727272727273e-06, |
| "loss": 2.3110013008117676, |
| "step": 41 |
| }, |
| { |
| "epoch": 2.1, |
| "grad_norm": 3.496481418609619, |
| "learning_rate": 6.90909090909091e-06, |
| "loss": 2.2765350341796875, |
| "step": 42 |
| }, |
| { |
| "epoch": 2.15, |
| "grad_norm": 4.4078521728515625, |
| "learning_rate": 6.545454545454546e-06, |
| "loss": 2.1151509284973145, |
| "step": 43 |
| }, |
| { |
| "epoch": 2.2, |
| "grad_norm": 3.675241470336914, |
| "learning_rate": 6.181818181818182e-06, |
| "loss": 2.2393054962158203, |
| "step": 44 |
| }, |
| { |
| "epoch": 2.25, |
| "grad_norm": 3.396697998046875, |
| "learning_rate": 5.8181818181818185e-06, |
| "loss": 2.1648597717285156, |
| "step": 45 |
| }, |
| { |
| "epoch": 2.3, |
| "grad_norm": 3.339559555053711, |
| "learning_rate": 5.4545454545454545e-06, |
| "loss": 2.2685420513153076, |
| "step": 46 |
| }, |
| { |
| "epoch": 2.35, |
| "grad_norm": 3.053208351135254, |
| "learning_rate": 5.090909090909091e-06, |
| "loss": 2.165018320083618, |
| "step": 47 |
| }, |
| { |
| "epoch": 2.4, |
| "grad_norm": 3.0201759338378906, |
| "learning_rate": 4.727272727272728e-06, |
| "loss": 2.209331750869751, |
| "step": 48 |
| }, |
| { |
| "epoch": 2.45, |
| "grad_norm": 4.258513450622559, |
| "learning_rate": 4.363636363636364e-06, |
| "loss": 2.2944233417510986, |
| "step": 49 |
| }, |
| { |
| "epoch": 2.5, |
| "grad_norm": 3.0130438804626465, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 2.2511136531829834, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.5, |
| "eval_loss": 2.1459906101226807, |
| "eval_runtime": 0.4027, |
| "eval_samples_per_second": 24.835, |
| "eval_steps_per_second": 7.451, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.55, |
| "grad_norm": 3.0704660415649414, |
| "learning_rate": 3.6363636363636366e-06, |
| "loss": 2.046316146850586, |
| "step": 51 |
| }, |
| { |
| "epoch": 2.6, |
| "grad_norm": 3.510226249694824, |
| "learning_rate": 3.272727272727273e-06, |
| "loss": 2.2383902072906494, |
| "step": 52 |
| }, |
| { |
| "epoch": 2.65, |
| "grad_norm": 2.91780686378479, |
| "learning_rate": 2.9090909090909093e-06, |
| "loss": 2.0489413738250732, |
| "step": 53 |
| }, |
| { |
| "epoch": 2.7, |
| "grad_norm": 2.8892462253570557, |
| "learning_rate": 2.5454545454545456e-06, |
| "loss": 2.042137384414673, |
| "step": 54 |
| }, |
| { |
| "epoch": 2.75, |
| "grad_norm": 2.9248545169830322, |
| "learning_rate": 2.181818181818182e-06, |
| "loss": 2.2285079956054688, |
| "step": 55 |
| }, |
| { |
| "epoch": 2.8, |
| "grad_norm": 3.120967149734497, |
| "learning_rate": 1.8181818181818183e-06, |
| "loss": 2.1922335624694824, |
| "step": 56 |
| }, |
| { |
| "epoch": 2.85, |
| "grad_norm": 2.938640594482422, |
| "learning_rate": 1.4545454545454546e-06, |
| "loss": 2.115161895751953, |
| "step": 57 |
| }, |
| { |
| "epoch": 2.9, |
| "grad_norm": 3.638606309890747, |
| "learning_rate": 1.090909090909091e-06, |
| "loss": 2.0304441452026367, |
| "step": 58 |
| }, |
| { |
| "epoch": 2.95, |
| "grad_norm": 3.6058709621429443, |
| "learning_rate": 7.272727272727273e-07, |
| "loss": 2.1807315349578857, |
| "step": 59 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 3.680497407913208, |
| "learning_rate": 3.6363636363636366e-07, |
| "loss": 2.085890769958496, |
| "step": 60 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 2.1111679077148438, |
| "eval_runtime": 0.3942, |
| "eval_samples_per_second": 25.367, |
| "eval_steps_per_second": 7.61, |
| "step": 60 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 60, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 146320632391680.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
