| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11981428785382657, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005990714392691329, | |
| "eval_loss": 1.004752278327942, | |
| "eval_runtime": 70.7261, | |
| "eval_samples_per_second": 9.94, | |
| "eval_steps_per_second": 4.977, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0029953571963456643, | |
| "grad_norm": 0.18182222545146942, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9628, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0059907143926913285, | |
| "grad_norm": 0.332571804523468, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9078, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008986071589036993, | |
| "grad_norm": 0.37095582485198975, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 0.8518, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011981428785382657, | |
| "grad_norm": 0.2458864152431488, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 0.8069, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014976785981728321, | |
| "grad_norm": 0.27912917733192444, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 0.7939, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.017972143178073986, | |
| "grad_norm": 0.23648440837860107, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 0.7987, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020967500374419648, | |
| "grad_norm": 0.2283579260110855, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 0.7577, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.023962857570765314, | |
| "grad_norm": 0.25041672587394714, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 0.7453, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026958214767110977, | |
| "grad_norm": 0.2930695414543152, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 0.7829, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.029953571963456643, | |
| "grad_norm": 2.5345871448516846, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 0.8497, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.029953571963456643, | |
| "eval_loss": 0.7315021753311157, | |
| "eval_runtime": 71.6597, | |
| "eval_samples_per_second": 9.81, | |
| "eval_steps_per_second": 4.912, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.032948929159802305, | |
| "grad_norm": 0.24415665864944458, | |
| "learning_rate": 8.678619553365659e-05, | |
| "loss": 0.7032, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.03594428635614797, | |
| "grad_norm": 0.2278505265712738, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 0.719, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03893964355249364, | |
| "grad_norm": 0.22066064178943634, | |
| "learning_rate": 8.07106356344834e-05, | |
| "loss": 0.702, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.041935000748839296, | |
| "grad_norm": 0.2387736737728119, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.7632, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.04493035794518496, | |
| "grad_norm": 0.2650596797466278, | |
| "learning_rate": 7.379736965185368e-05, | |
| "loss": 0.732, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.04792571514153063, | |
| "grad_norm": 0.24967215955257416, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 0.7172, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.050921072337876294, | |
| "grad_norm": 0.286597341299057, | |
| "learning_rate": 6.623497346023418e-05, | |
| "loss": 0.7474, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.05391642953422195, | |
| "grad_norm": 0.3098317086696625, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.7112, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.05691178673056762, | |
| "grad_norm": 0.39849919080734253, | |
| "learning_rate": 5.8229729514036705e-05, | |
| "loss": 0.725, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.059907143926913285, | |
| "grad_norm": 0.8537949919700623, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.6799, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.059907143926913285, | |
| "eval_loss": 0.696488618850708, | |
| "eval_runtime": 71.5155, | |
| "eval_samples_per_second": 9.83, | |
| "eval_steps_per_second": 4.922, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06290250112325894, | |
| "grad_norm": 0.29265350103378296, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6978, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.06589785831960461, | |
| "grad_norm": 0.252399742603302, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.691, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.06889321551595028, | |
| "grad_norm": 0.3063851594924927, | |
| "learning_rate": 4.17702704859633e-05, | |
| "loss": 0.6782, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.07188857271229594, | |
| "grad_norm": 0.29295191168785095, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.6746, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.07488392990864161, | |
| "grad_norm": 0.30502256751060486, | |
| "learning_rate": 3.3765026539765834e-05, | |
| "loss": 0.6952, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.07787928710498727, | |
| "grad_norm": 0.31604963541030884, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.7081, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.08087464430133294, | |
| "grad_norm": 0.327537477016449, | |
| "learning_rate": 2.6202630348146324e-05, | |
| "loss": 0.6665, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.08387000149767859, | |
| "grad_norm": 0.3402194678783417, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.7172, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.08686535869402426, | |
| "grad_norm": 0.4145227074623108, | |
| "learning_rate": 1.928936436551661e-05, | |
| "loss": 0.7087, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.08986071589036992, | |
| "grad_norm": 1.363573670387268, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.6827, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.08986071589036992, | |
| "eval_loss": 0.6812626719474792, | |
| "eval_runtime": 71.5525, | |
| "eval_samples_per_second": 9.825, | |
| "eval_steps_per_second": 4.919, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09285607308671559, | |
| "grad_norm": 0.2718447148799896, | |
| "learning_rate": 1.3213804466343421e-05, | |
| "loss": 0.6568, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.09585143028306126, | |
| "grad_norm": 0.28798407316207886, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.644, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.09884678747940692, | |
| "grad_norm": 0.2958885431289673, | |
| "learning_rate": 8.141676086873572e-06, | |
| "loss": 0.6633, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.10184214467575259, | |
| "grad_norm": 0.27504944801330566, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.6562, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.10483750187209825, | |
| "grad_norm": 0.31736892461776733, | |
| "learning_rate": 4.2113336672471245e-06, | |
| "loss": 0.7045, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.1078328590684439, | |
| "grad_norm": 0.3362809121608734, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.7204, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.11082821626478957, | |
| "grad_norm": 0.3363928496837616, | |
| "learning_rate": 1.5299867030334814e-06, | |
| "loss": 0.7207, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.11382357346113524, | |
| "grad_norm": 0.375256210565567, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.6748, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.1168189306574809, | |
| "grad_norm": 0.4309163987636566, | |
| "learning_rate": 1.7077534966650766e-07, | |
| "loss": 0.7076, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.11981428785382657, | |
| "grad_norm": 1.0810436010360718, | |
| "learning_rate": 0.0, | |
| "loss": 0.6669, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11981428785382657, | |
| "eval_loss": 0.6776874661445618, | |
| "eval_runtime": 71.5803, | |
| "eval_samples_per_second": 9.821, | |
| "eval_steps_per_second": 4.918, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.469809826103296e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |