| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9470124013528749, |
| "eval_steps": 10, |
| "global_step": 210, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.04509582863585118, |
| "grad_norm": 4.649589538574219, |
| "learning_rate": 1.173913043478261e-06, |
| "loss": 1.6576, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04509582863585118, |
| "eval_loss": 1.9276622533798218, |
| "eval_runtime": 13.2788, |
| "eval_samples_per_second": 14.083, |
| "eval_steps_per_second": 7.079, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.09019165727170236, |
| "grad_norm": 3.7612740993499756, |
| "learning_rate": 2.4782608695652173e-06, |
| "loss": 1.6856, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.09019165727170236, |
| "eval_loss": 1.8389543294906616, |
| "eval_runtime": 13.2051, |
| "eval_samples_per_second": 14.161, |
| "eval_steps_per_second": 7.118, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.13528748590755355, |
| "grad_norm": 3.048597812652588, |
| "learning_rate": 2.993785263797297e-06, |
| "loss": 1.5539, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.13528748590755355, |
| "eval_loss": 1.6339466571807861, |
| "eval_runtime": 13.2214, |
| "eval_samples_per_second": 14.144, |
| "eval_steps_per_second": 7.11, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.18038331454340473, |
| "grad_norm": 1.3381422758102417, |
| "learning_rate": 2.9559926521749324e-06, |
| "loss": 1.6382, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.18038331454340473, |
| "eval_loss": 1.478708028793335, |
| "eval_runtime": 13.3673, |
| "eval_samples_per_second": 13.989, |
| "eval_steps_per_second": 7.032, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2254791431792559, |
| "grad_norm": 0.7458074688911438, |
| "learning_rate": 2.8847278242602185e-06, |
| "loss": 1.2616, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2254791431792559, |
| "eval_loss": 1.407120943069458, |
| "eval_runtime": 13.2044, |
| "eval_samples_per_second": 14.162, |
| "eval_steps_per_second": 7.119, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2705749718151071, |
| "grad_norm": 0.6770926713943481, |
| "learning_rate": 2.7816291068197328e-06, |
| "loss": 1.2366, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.2705749718151071, |
| "eval_loss": 1.3675240278244019, |
| "eval_runtime": 13.4556, |
| "eval_samples_per_second": 13.898, |
| "eval_steps_per_second": 6.986, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.3156708004509583, |
| "grad_norm": 0.7203531265258789, |
| "learning_rate": 2.649066664678467e-06, |
| "loss": 1.3251, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.3156708004509583, |
| "eval_loss": 1.3370201587677002, |
| "eval_runtime": 13.2298, |
| "eval_samples_per_second": 14.135, |
| "eval_steps_per_second": 7.105, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.36076662908680945, |
| "grad_norm": 0.6693026423454285, |
| "learning_rate": 2.4900880123475463e-06, |
| "loss": 1.2595, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.36076662908680945, |
| "eval_loss": 1.3134440183639526, |
| "eval_runtime": 13.3078, |
| "eval_samples_per_second": 14.052, |
| "eval_steps_per_second": 7.064, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.40586245772266066, |
| "grad_norm": 0.5636974573135376, |
| "learning_rate": 2.3083479538733636e-06, |
| "loss": 1.0858, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.40586245772266066, |
| "eval_loss": 1.2941912412643433, |
| "eval_runtime": 13.1999, |
| "eval_samples_per_second": 14.167, |
| "eval_steps_per_second": 7.121, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.4509582863585118, |
| "grad_norm": 0.571853756904602, |
| "learning_rate": 2.108024561540242e-06, |
| "loss": 1.2219, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.4509582863585118, |
| "eval_loss": 1.2784264087677002, |
| "eval_runtime": 13.24, |
| "eval_samples_per_second": 14.124, |
| "eval_steps_per_second": 7.1, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.496054114994363, |
| "grad_norm": 0.5300303101539612, |
| "learning_rate": 1.8937231250153905e-06, |
| "loss": 1.1319, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.496054114994363, |
| "eval_loss": 1.264504313468933, |
| "eval_runtime": 13.2023, |
| "eval_samples_per_second": 14.164, |
| "eval_steps_per_second": 7.12, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.5411499436302142, |
| "grad_norm": 0.5525142550468445, |
| "learning_rate": 1.6703702790757123e-06, |
| "loss": 1.1702, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5411499436302142, |
| "eval_loss": 1.2530410289764404, |
| "eval_runtime": 13.2204, |
| "eval_samples_per_second": 14.145, |
| "eval_steps_per_second": 7.11, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.5862457722660653, |
| "grad_norm": 0.3444017171859741, |
| "learning_rate": 1.4431007438433431e-06, |
| "loss": 1.1054, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.5862457722660653, |
| "eval_loss": 1.2430415153503418, |
| "eval_runtime": 13.205, |
| "eval_samples_per_second": 14.161, |
| "eval_steps_per_second": 7.119, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.6313416009019166, |
| "grad_norm": 0.5441855192184448, |
| "learning_rate": 1.2171392812898465e-06, |
| "loss": 1.1249, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6313416009019166, |
| "eval_loss": 1.2348647117614746, |
| "eval_runtime": 13.2648, |
| "eval_samples_per_second": 14.097, |
| "eval_steps_per_second": 7.086, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.6764374295377678, |
| "grad_norm": 0.5227693915367126, |
| "learning_rate": 9.976805817435208e-07, |
| "loss": 1.1867, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.6764374295377678, |
| "eval_loss": 1.2283574342727661, |
| "eval_runtime": 13.1435, |
| "eval_samples_per_second": 14.228, |
| "eval_steps_per_second": 7.152, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.7215332581736189, |
| "grad_norm": 0.542244017124176, |
| "learning_rate": 7.89769841721999e-07, |
| "loss": 1.0513, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7215332581736189, |
| "eval_loss": 1.223202109336853, |
| "eval_runtime": 13.3114, |
| "eval_samples_per_second": 14.048, |
| "eval_steps_per_second": 7.062, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.7666290868094702, |
| "grad_norm": 0.43865886330604553, |
| "learning_rate": 5.98186778519257e-07, |
| "loss": 1.1238, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.7666290868094702, |
| "eval_loss": 1.2190639972686768, |
| "eval_runtime": 13.2662, |
| "eval_samples_per_second": 14.096, |
| "eval_steps_per_second": 7.086, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.8117249154453213, |
| "grad_norm": 0.4573892056941986, |
| "learning_rate": 4.273357479676508e-07, |
| "loss": 1.1548, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.8117249154453213, |
| "eval_loss": 1.2160392999649048, |
| "eval_runtime": 13.1667, |
| "eval_samples_per_second": 14.203, |
| "eval_steps_per_second": 7.139, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.8568207440811725, |
| "grad_norm": 0.476138710975647, |
| "learning_rate": 2.8114449148802547e-07, |
| "loss": 1.2207, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.8568207440811725, |
| "eval_loss": 1.2139577865600586, |
| "eval_runtime": 13.1987, |
| "eval_samples_per_second": 14.168, |
| "eval_steps_per_second": 7.122, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.9019165727170236, |
| "grad_norm": 0.4513246715068817, |
| "learning_rate": 1.6297384015986928e-07, |
| "loss": 1.1339, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9019165727170236, |
| "eval_loss": 1.212600827217102, |
| "eval_runtime": 13.239, |
| "eval_samples_per_second": 14.125, |
| "eval_steps_per_second": 7.1, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9470124013528749, |
| "grad_norm": 0.4398881196975708, |
| "learning_rate": 7.554045164952123e-08, |
| "loss": 1.0351, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.9470124013528749, |
| "eval_loss": 1.21186363697052, |
| "eval_runtime": 13.2875, |
| "eval_samples_per_second": 14.073, |
| "eval_steps_per_second": 7.074, |
| "step": 210 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 230, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 3.622155888280781e+16, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
