| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.663900414937759, | |
| "eval_steps": 500, | |
| "global_step": 80, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03319502074688797, | |
| "grad_norm": 8.615787895890602, | |
| "learning_rate": 0.0, | |
| "loss": 1.3636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06639004149377593, | |
| "grad_norm": 8.559176870090305, | |
| "learning_rate": 2.666666666666667e-06, | |
| "loss": 1.39, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0995850622406639, | |
| "grad_norm": 7.763393937169438, | |
| "learning_rate": 5.333333333333334e-06, | |
| "loss": 1.3674, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13278008298755187, | |
| "grad_norm": 3.1671709519080324, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.2173, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16597510373443983, | |
| "grad_norm": 3.04503337779613, | |
| "learning_rate": 1.0666666666666667e-05, | |
| "loss": 1.0941, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1991701244813278, | |
| "grad_norm": 2.989964302933358, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 1.1226, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.23236514522821577, | |
| "grad_norm": 3.459388997412336, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 1.0734, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.26556016597510373, | |
| "grad_norm": 2.533839407605375, | |
| "learning_rate": 1.866666666666667e-05, | |
| "loss": 1.0045, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2987551867219917, | |
| "grad_norm": 2.8224948362089712, | |
| "learning_rate": 2.1333333333333335e-05, | |
| "loss": 0.9903, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.33195020746887965, | |
| "grad_norm": 2.1132471970550197, | |
| "learning_rate": 2.4e-05, | |
| "loss": 0.9568, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3651452282157676, | |
| "grad_norm": 1.8276852389668479, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.945, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3983402489626556, | |
| "grad_norm": 1.9070208027494653, | |
| "learning_rate": 2.9333333333333333e-05, | |
| "loss": 0.8958, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4315352697095436, | |
| "grad_norm": 1.5086701253320605, | |
| "learning_rate": 3.2000000000000005e-05, | |
| "loss": 0.8932, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.46473029045643155, | |
| "grad_norm": 1.6692252959799796, | |
| "learning_rate": 3.466666666666667e-05, | |
| "loss": 0.8899, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4979253112033195, | |
| "grad_norm": 1.5543883507537406, | |
| "learning_rate": 3.733333333333334e-05, | |
| "loss": 0.8962, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5311203319502075, | |
| "grad_norm": 1.5207028288253677, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8958, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5643153526970954, | |
| "grad_norm": 1.3772276740689315, | |
| "learning_rate": 3.999458482358924e-05, | |
| "loss": 0.8678, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5975103734439834, | |
| "grad_norm": 1.2350882249364952, | |
| "learning_rate": 3.99783422267705e-05, | |
| "loss": 0.8698, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6307053941908713, | |
| "grad_norm": 1.5168399267769646, | |
| "learning_rate": 3.9951281005196486e-05, | |
| "loss": 0.8467, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6639004149377593, | |
| "grad_norm": 0.9947073114646282, | |
| "learning_rate": 3.991341581299609e-05, | |
| "loss": 0.851, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6970954356846473, | |
| "grad_norm": 1.3721835937192417, | |
| "learning_rate": 3.9864767154838864e-05, | |
| "loss": 0.8212, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7302904564315352, | |
| "grad_norm": 1.1421321822572974, | |
| "learning_rate": 3.980536137483141e-05, | |
| "loss": 0.8349, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7634854771784232, | |
| "grad_norm": 1.158024116310333, | |
| "learning_rate": 3.973523064225159e-05, | |
| "loss": 0.8199, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7966804979253111, | |
| "grad_norm": 0.8300618356114078, | |
| "learning_rate": 3.965441293412827e-05, | |
| "loss": 0.8362, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8298755186721992, | |
| "grad_norm": 0.9468275757503992, | |
| "learning_rate": 3.9562952014676116e-05, | |
| "loss": 0.8168, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8630705394190872, | |
| "grad_norm": 0.9398559845087756, | |
| "learning_rate": 3.946089741159648e-05, | |
| "loss": 0.8171, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8962655601659751, | |
| "grad_norm": 0.9485219729922953, | |
| "learning_rate": 3.934830438925728e-05, | |
| "loss": 0.8012, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.9294605809128631, | |
| "grad_norm": 1.0308850725665082, | |
| "learning_rate": 3.922523391876638e-05, | |
| "loss": 0.7854, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9626556016597511, | |
| "grad_norm": 1.20395138490915, | |
| "learning_rate": 3.909175264495464e-05, | |
| "loss": 0.8047, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.995850622406639, | |
| "grad_norm": 0.8448920980747194, | |
| "learning_rate": 3.8947932850286585e-05, | |
| "loss": 0.7854, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.033195020746888, | |
| "grad_norm": 2.245209172954801, | |
| "learning_rate": 3.879385241571817e-05, | |
| "loss": 1.5149, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.066390041493776, | |
| "grad_norm": 0.9134845133034926, | |
| "learning_rate": 3.862959477852285e-05, | |
| "loss": 0.7548, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.099585062240664, | |
| "grad_norm": 0.9930546625802095, | |
| "learning_rate": 3.845524888710885e-05, | |
| "loss": 0.759, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1327800829875518, | |
| "grad_norm": 0.77588901645867, | |
| "learning_rate": 3.827090915285202e-05, | |
| "loss": 0.7341, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.16597510373444, | |
| "grad_norm": 0.6668617646330832, | |
| "learning_rate": 3.807667539897041e-05, | |
| "loss": 0.7416, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1991701244813278, | |
| "grad_norm": 0.78348508679161, | |
| "learning_rate": 3.787265280646825e-05, | |
| "loss": 0.7404, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2323651452282158, | |
| "grad_norm": 1.064645095474325, | |
| "learning_rate": 3.7658951857178544e-05, | |
| "loss": 0.7479, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2655601659751037, | |
| "grad_norm": 0.7188618680855522, | |
| "learning_rate": 3.743568827393525e-05, | |
| "loss": 0.7191, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2987551867219918, | |
| "grad_norm": 0.8332631243928624, | |
| "learning_rate": 3.720298295790732e-05, | |
| "loss": 0.7132, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.3319502074688796, | |
| "grad_norm": 0.7102694689937566, | |
| "learning_rate": 3.696096192312852e-05, | |
| "loss": 0.7087, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3651452282157677, | |
| "grad_norm": 0.6710612259560924, | |
| "learning_rate": 3.6709756228258735e-05, | |
| "loss": 0.7257, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3983402489626555, | |
| "grad_norm": 0.6935377627613012, | |
| "learning_rate": 3.644950190561325e-05, | |
| "loss": 0.732, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4315352697095436, | |
| "grad_norm": 0.6345437504230033, | |
| "learning_rate": 3.6180339887498953e-05, | |
| "loss": 0.7285, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4647302904564317, | |
| "grad_norm": 0.569179877257485, | |
| "learning_rate": 3.590241592989696e-05, | |
| "loss": 0.7272, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4979253112033195, | |
| "grad_norm": 0.5638090957495433, | |
| "learning_rate": 3.561588053353319e-05, | |
| "loss": 0.724, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.5311203319502074, | |
| "grad_norm": 0.6847005696091287, | |
| "learning_rate": 3.532088886237956e-05, | |
| "loss": 0.7303, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5643153526970954, | |
| "grad_norm": 0.7137303594813845, | |
| "learning_rate": 3.5017600659629986e-05, | |
| "loss": 0.7226, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5975103734439835, | |
| "grad_norm": 0.6692629863007482, | |
| "learning_rate": 3.470618016119658e-05, | |
| "loss": 0.7317, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6307053941908713, | |
| "grad_norm": 0.6130719713014338, | |
| "learning_rate": 3.438679600677303e-05, | |
| "loss": 0.7135, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6639004149377592, | |
| "grad_norm": 0.7269780774769957, | |
| "learning_rate": 3.405962114851324e-05, | |
| "loss": 0.7069, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6970954356846473, | |
| "grad_norm": 0.7675385685925549, | |
| "learning_rate": 3.372483275737468e-05, | |
| "loss": 0.6947, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 1.7302904564315353, | |
| "grad_norm": 0.5557654669776614, | |
| "learning_rate": 3.3382612127177166e-05, | |
| "loss": 0.7114, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 1.7634854771784232, | |
| "grad_norm": 0.843893721004563, | |
| "learning_rate": 3.303314457642911e-05, | |
| "loss": 0.6951, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 1.796680497925311, | |
| "grad_norm": 0.7044204542667526, | |
| "learning_rate": 3.26766193479742e-05, | |
| "loss": 0.7102, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.8298755186721993, | |
| "grad_norm": 0.5932946307804874, | |
| "learning_rate": 3.2313229506513167e-05, | |
| "loss": 0.6879, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.8630705394190872, | |
| "grad_norm": 0.5180970490499838, | |
| "learning_rate": 3.194317183405573e-05, | |
| "loss": 0.694, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.896265560165975, | |
| "grad_norm": 0.7223180987342492, | |
| "learning_rate": 3.156664672335973e-05, | |
| "loss": 0.7043, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.929460580912863, | |
| "grad_norm": 0.6156946074167337, | |
| "learning_rate": 3.1183858069414936e-05, | |
| "loss": 0.7018, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.9626556016597512, | |
| "grad_norm": 0.6661521028388685, | |
| "learning_rate": 3.079501315903026e-05, | |
| "loss": 0.713, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.995850622406639, | |
| "grad_norm": 0.57891277679672, | |
| "learning_rate": 3.0400322558584308e-05, | |
| "loss": 0.7126, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.033195020746888, | |
| "grad_norm": 2.0063313681311743, | |
| "learning_rate": 3.0000000000000004e-05, | |
| "loss": 1.3315, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.066390041493776, | |
| "grad_norm": 0.7924238362204284, | |
| "learning_rate": 2.959426226500493e-05, | |
| "loss": 0.6405, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.099585062240664, | |
| "grad_norm": 0.8652584407517231, | |
| "learning_rate": 2.9183329067740235e-05, | |
| "loss": 0.6286, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.132780082987552, | |
| "grad_norm": 0.717303390179401, | |
| "learning_rate": 2.876742293578155e-05, | |
| "loss": 0.6204, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.1659751037344397, | |
| "grad_norm": 0.9109192659165971, | |
| "learning_rate": 2.834676908963636e-05, | |
| "loss": 0.6279, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.199170124481328, | |
| "grad_norm": 0.8861815091608722, | |
| "learning_rate": 2.792159532078314e-05, | |
| "loss": 0.6249, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.232365145228216, | |
| "grad_norm": 0.7504327505581353, | |
| "learning_rate": 2.7492131868318247e-05, | |
| "loss": 0.6296, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.2655601659751037, | |
| "grad_norm": 0.7468142972930245, | |
| "learning_rate": 2.7058611294277378e-05, | |
| "loss": 0.6328, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.2987551867219915, | |
| "grad_norm": 0.782870677435499, | |
| "learning_rate": 2.6621268357699165e-05, | |
| "loss": 0.6181, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.33195020746888, | |
| "grad_norm": 0.5486446333222698, | |
| "learning_rate": 2.618033988749895e-05, | |
| "loss": 0.6202, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.3651452282157677, | |
| "grad_norm": 0.6140586451457445, | |
| "learning_rate": 2.5736064654221808e-05, | |
| "loss": 0.6123, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.3983402489626555, | |
| "grad_norm": 0.5685554543391838, | |
| "learning_rate": 2.528868324074405e-05, | |
| "loss": 0.6197, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.431535269709544, | |
| "grad_norm": 0.5711825546726801, | |
| "learning_rate": 2.4838437911993355e-05, | |
| "loss": 0.6256, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.4647302904564317, | |
| "grad_norm": 0.7020688481999959, | |
| "learning_rate": 2.4385572483758066e-05, | |
| "loss": 0.6086, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.4979253112033195, | |
| "grad_norm": 0.5087577150668112, | |
| "learning_rate": 2.3930332190656604e-05, | |
| "loss": 0.611, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 2.5311203319502074, | |
| "grad_norm": 0.6537825147166224, | |
| "learning_rate": 2.3472963553338614e-05, | |
| "loss": 0.6193, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.564315352697095, | |
| "grad_norm": 0.45499946823109266, | |
| "learning_rate": 2.3013714244989665e-05, | |
| "loss": 0.6071, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 2.5975103734439835, | |
| "grad_norm": 0.6174423025200944, | |
| "learning_rate": 2.25528329572119e-05, | |
| "loss": 0.617, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 2.6307053941908713, | |
| "grad_norm": 0.4778613015683359, | |
| "learning_rate": 2.209056926535307e-05, | |
| "loss": 0.6067, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 2.663900414937759, | |
| "grad_norm": 0.556533197381377, | |
| "learning_rate": 2.1627173493357167e-05, | |
| "loss": 0.6044, | |
| "step": 80 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 150, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.466139400429896e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |