| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04240957042639289, | |
| "eval_steps": 500, | |
| "global_step": 2400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008835327172165185, | |
| "grad_norm": 5.665971279144287, | |
| "learning_rate": 4.3286219081272084e-07, | |
| "loss": 1.3738, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001767065434433037, | |
| "grad_norm": 5.6161651611328125, | |
| "learning_rate": 8.745583038869259e-07, | |
| "loss": 1.1661, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0026505981516495554, | |
| "grad_norm": 7.866199970245361, | |
| "learning_rate": 1.3162544169611309e-06, | |
| "loss": 1.2107, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.003534130868866074, | |
| "grad_norm": 5.07379674911499, | |
| "learning_rate": 1.7579505300353357e-06, | |
| "loss": 0.9855, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.004417663586082593, | |
| "grad_norm": 3.2607851028442383, | |
| "learning_rate": 2.199646643109541e-06, | |
| "loss": 0.9431, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.005301196303299111, | |
| "grad_norm": 6.517599105834961, | |
| "learning_rate": 2.6413427561837457e-06, | |
| "loss": 0.8566, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.00618472902051563, | |
| "grad_norm": 2.8523333072662354, | |
| "learning_rate": 3.0830388692579506e-06, | |
| "loss": 0.8697, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.007068261737732148, | |
| "grad_norm": 3.460226058959961, | |
| "learning_rate": 3.5247349823321555e-06, | |
| "loss": 0.8099, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.007951794454948667, | |
| "grad_norm": 3.2528891563415527, | |
| "learning_rate": 3.966431095406361e-06, | |
| "loss": 0.766, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.008835327172165185, | |
| "grad_norm": 4.1086039543151855, | |
| "learning_rate": 4.408127208480566e-06, | |
| "loss": 0.7402, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.009718859889381704, | |
| "grad_norm": 3.8160510063171387, | |
| "learning_rate": 4.849823321554771e-06, | |
| "loss": 0.8769, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.010602392606598222, | |
| "grad_norm": 2.901653289794922, | |
| "learning_rate": 5.291519434628975e-06, | |
| "loss": 0.6827, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.011485925323814742, | |
| "grad_norm": 2.5824739933013916, | |
| "learning_rate": 5.73321554770318e-06, | |
| "loss": 0.7252, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.01236945804103126, | |
| "grad_norm": 2.586138963699341, | |
| "learning_rate": 6.174911660777385e-06, | |
| "loss": 0.7701, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.013252990758247778, | |
| "grad_norm": 2.3450210094451904, | |
| "learning_rate": 6.6166077738515904e-06, | |
| "loss": 0.7525, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.014136523475464296, | |
| "grad_norm": 2.7902042865753174, | |
| "learning_rate": 7.058303886925795e-06, | |
| "loss": 0.7097, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.015020056192680814, | |
| "grad_norm": 3.297929286956787, | |
| "learning_rate": 7.5e-06, | |
| "loss": 0.7575, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.015903588909897334, | |
| "grad_norm": 4.028406143188477, | |
| "learning_rate": 7.941696113074205e-06, | |
| "loss": 0.6899, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.016787121627113853, | |
| "grad_norm": 2.2513041496276855, | |
| "learning_rate": 8.38339222614841e-06, | |
| "loss": 0.6655, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.01767065434433037, | |
| "grad_norm": 2.402355670928955, | |
| "learning_rate": 8.825088339222614e-06, | |
| "loss": 0.6601, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.01855418706154689, | |
| "grad_norm": 4.492621898651123, | |
| "learning_rate": 9.26678445229682e-06, | |
| "loss": 0.6925, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.019437719778763407, | |
| "grad_norm": 3.8099517822265625, | |
| "learning_rate": 9.708480565371025e-06, | |
| "loss": 0.6169, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.020321252495979925, | |
| "grad_norm": 4.58193826675415, | |
| "learning_rate": 1.0150176678445231e-05, | |
| "loss": 0.6367, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.021204785213196443, | |
| "grad_norm": 4.745123863220215, | |
| "learning_rate": 1.0591872791519434e-05, | |
| "loss": 0.615, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.02208831793041296, | |
| "grad_norm": 3.260239601135254, | |
| "learning_rate": 1.103356890459364e-05, | |
| "loss": 0.6869, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.022971850647629483, | |
| "grad_norm": 2.485383987426758, | |
| "learning_rate": 1.1475265017667845e-05, | |
| "loss": 0.7527, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.023855383364846, | |
| "grad_norm": 2.26680326461792, | |
| "learning_rate": 1.191696113074205e-05, | |
| "loss": 0.6124, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.02473891608206252, | |
| "grad_norm": 2.348688840866089, | |
| "learning_rate": 1.2358657243816255e-05, | |
| "loss": 0.6511, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.025622448799279038, | |
| "grad_norm": 2.770859956741333, | |
| "learning_rate": 1.280035335689046e-05, | |
| "loss": 0.7047, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.026505981516495556, | |
| "grad_norm": 3.188656806945801, | |
| "learning_rate": 1.3242049469964666e-05, | |
| "loss": 0.6639, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.027389514233712074, | |
| "grad_norm": 2.7158899307250977, | |
| "learning_rate": 1.368374558303887e-05, | |
| "loss": 0.6795, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.028273046950928592, | |
| "grad_norm": 2.7986080646514893, | |
| "learning_rate": 1.4125441696113076e-05, | |
| "loss": 0.6341, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.02915657966814511, | |
| "grad_norm": 1.9698214530944824, | |
| "learning_rate": 1.456713780918728e-05, | |
| "loss": 0.6031, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.03004011238536163, | |
| "grad_norm": 2.495985507965088, | |
| "learning_rate": 1.5008833922261484e-05, | |
| "loss": 0.5959, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.030923645102578147, | |
| "grad_norm": 2.990360975265503, | |
| "learning_rate": 1.545053003533569e-05, | |
| "loss": 0.6412, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.03180717781979467, | |
| "grad_norm": 3.658212184906006, | |
| "learning_rate": 1.5892226148409894e-05, | |
| "loss": 0.5065, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.03269071053701118, | |
| "grad_norm": 2.010875940322876, | |
| "learning_rate": 1.63339222614841e-05, | |
| "loss": 0.5611, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.033574243254227705, | |
| "grad_norm": 2.408937692642212, | |
| "learning_rate": 1.6775618374558306e-05, | |
| "loss": 0.5298, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.03445777597144422, | |
| "grad_norm": 2.3144407272338867, | |
| "learning_rate": 1.721731448763251e-05, | |
| "loss": 0.5759, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.03534130868866074, | |
| "grad_norm": 2.944115400314331, | |
| "learning_rate": 1.7659010600706715e-05, | |
| "loss": 0.5782, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.03622484140587726, | |
| "grad_norm": 2.3239428997039795, | |
| "learning_rate": 1.810070671378092e-05, | |
| "loss": 0.5221, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.03710837412309378, | |
| "grad_norm": 4.565939426422119, | |
| "learning_rate": 1.8542402826855124e-05, | |
| "loss": 0.5966, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.0379919068403103, | |
| "grad_norm": 2.6089091300964355, | |
| "learning_rate": 1.898409893992933e-05, | |
| "loss": 0.5989, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.038875439557526814, | |
| "grad_norm": 2.4395945072174072, | |
| "learning_rate": 1.9425795053003533e-05, | |
| "loss": 0.5097, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.039758972274743336, | |
| "grad_norm": 2.274600028991699, | |
| "learning_rate": 1.986749116607774e-05, | |
| "loss": 0.4934, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.04064250499195985, | |
| "grad_norm": 2.393251895904541, | |
| "learning_rate": 2.0309187279151945e-05, | |
| "loss": 0.5354, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.04152603770917637, | |
| "grad_norm": 2.613900899887085, | |
| "learning_rate": 2.075088339222615e-05, | |
| "loss": 0.5236, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.04240957042639289, | |
| "grad_norm": 2.233302116394043, | |
| "learning_rate": 2.1192579505300354e-05, | |
| "loss": 0.5057, | |
| "step": 2400 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 56591, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 256, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |