| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 39, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07692307692307693, |
| "grad_norm": 0.011006172946138796, |
| "learning_rate": 2e-05, |
| "loss": 0.2391, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.15384615384615385, |
| "grad_norm": 0.009920294569357094, |
| "learning_rate": 4e-05, |
| "loss": 0.2609, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.23076923076923078, |
| "grad_norm": 0.01158092107894398, |
| "learning_rate": 6.000000000000001e-05, |
| "loss": 0.2587, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.3076923076923077, |
| "grad_norm": 0.0201005612255337, |
| "learning_rate": 8e-05, |
| "loss": 0.2712, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.38461538461538464, |
| "grad_norm": 0.013449641741916138, |
| "learning_rate": 7.983897175980957e-05, |
| "loss": 0.2408, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.46153846153846156, |
| "grad_norm": 0.017403662565344077, |
| "learning_rate": 7.93571835439452e-05, |
| "loss": 0.2277, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.5384615384615384, |
| "grad_norm": 0.016783900205254377, |
| "learning_rate": 7.855851442783414e-05, |
| "loss": 0.2281, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.6153846153846154, |
| "grad_norm": 0.013041582389936975, |
| "learning_rate": 7.74493948255895e-05, |
| "loss": 0.2127, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.6923076923076923, |
| "grad_norm": 0.008599268410488753, |
| "learning_rate": 7.603875471609677e-05, |
| "loss": 0.2198, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 0.009272083398470401, |
| "learning_rate": 7.433795174407465e-05, |
| "loss": 0.2537, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.8461538461538461, |
| "grad_norm": 0.017009886825312504, |
| "learning_rate": 7.236067977499791e-05, |
| "loss": 0.1931, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.9230769230769231, |
| "grad_norm": 0.019269587613227883, |
| "learning_rate": 7.012285864014445e-05, |
| "loss": 0.23, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.01921119861962993, |
| "learning_rate": 6.76425059594746e-05, |
| "loss": 0.2169, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.0769230769230769, |
| "grad_norm": 0.016008391623032813, |
| "learning_rate": 6.493959207434934e-05, |
| "loss": 0.2231, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.1538461538461537, |
| "grad_norm": 0.013505093256517267, |
| "learning_rate": 6.20358792580841e-05, |
| "loss": 0.216, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.2307692307692308, |
| "grad_norm": 0.009118977222006231, |
| "learning_rate": 5.895474649891995e-05, |
| "loss": 0.1955, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.3076923076923077, |
| "grad_norm": 0.008130055798965707, |
| "learning_rate": 5.572100126615695e-05, |
| "loss": 0.2379, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.3846153846153846, |
| "grad_norm": 0.008040382267002854, |
| "learning_rate": 5.23606797749979e-05, |
| "loss": 0.1926, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.4615384615384617, |
| "grad_norm": 0.007985366963191003, |
| "learning_rate": 4.890083735825258e-05, |
| "loss": 0.196, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.5384615384615383, |
| "grad_norm": 0.009022742061822532, |
| "learning_rate": 4.5369330632706223e-05, |
| "loss": 0.173, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.6153846153846154, |
| "grad_norm": 0.010255624399866037, |
| "learning_rate": 4.17945932140206e-05, |
| "loss": 0.2147, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.6923076923076923, |
| "grad_norm": 0.009741555715518118, |
| "learning_rate": 3.820540678597942e-05, |
| "loss": 0.1592, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.7692307692307692, |
| "grad_norm": 0.009844925309939856, |
| "learning_rate": 3.4630669367293797e-05, |
| "loss": 0.2045, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.8461538461538463, |
| "grad_norm": 0.010438901552927702, |
| "learning_rate": 3.109916264174743e-05, |
| "loss": 0.1494, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.9230769230769231, |
| "grad_norm": 0.010622270315970113, |
| "learning_rate": 2.7639320225002108e-05, |
| "loss": 0.2134, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.009659972608976171, |
| "learning_rate": 2.427899873384306e-05, |
| "loss": 0.205, |
| "step": 26 |
| }, |
| { |
| "epoch": 2.076923076923077, |
| "grad_norm": 0.010916832572563411, |
| "learning_rate": 2.1045253501080058e-05, |
| "loss": 0.1858, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.1538461538461537, |
| "grad_norm": 0.009749675363732882, |
| "learning_rate": 1.7964120741915905e-05, |
| "loss": 0.1672, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.230769230769231, |
| "grad_norm": 0.008711108100307416, |
| "learning_rate": 1.5060407925650662e-05, |
| "loss": 0.1883, |
| "step": 29 |
| }, |
| { |
| "epoch": 2.3076923076923075, |
| "grad_norm": 0.009348284679650916, |
| "learning_rate": 1.2357494040525416e-05, |
| "loss": 0.1577, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.3846153846153846, |
| "grad_norm": 0.008395179602647181, |
| "learning_rate": 9.877141359855567e-06, |
| "loss": 0.1929, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.4615384615384617, |
| "grad_norm": 0.00858698129154695, |
| "learning_rate": 7.639320225002106e-06, |
| "loss": 0.1485, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.5384615384615383, |
| "grad_norm": 0.008945513764739278, |
| "learning_rate": 5.662048255925357e-06, |
| "loss": 0.2167, |
| "step": 33 |
| }, |
| { |
| "epoch": 2.6153846153846154, |
| "grad_norm": 0.008857533620105983, |
| "learning_rate": 3.961245283903239e-06, |
| "loss": 0.1906, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.6923076923076925, |
| "grad_norm": 0.00837899269292367, |
| "learning_rate": 2.550605174410512e-06, |
| "loss": 0.1738, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.769230769230769, |
| "grad_norm": 0.008534100646481335, |
| "learning_rate": 1.4414855721658705e-06, |
| "loss": 0.1838, |
| "step": 36 |
| }, |
| { |
| "epoch": 2.8461538461538463, |
| "grad_norm": 0.008482103570619792, |
| "learning_rate": 6.428164560548134e-07, |
| "loss": 0.1508, |
| "step": 37 |
| }, |
| { |
| "epoch": 2.9230769230769234, |
| "grad_norm": 0.00892411300486341, |
| "learning_rate": 1.6102824019043728e-07, |
| "loss": 0.1676, |
| "step": 38 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.008871456118818033, |
| "learning_rate": 0.0, |
| "loss": 0.1878, |
| "step": 39 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 39, |
| "total_flos": 88667793129472.0, |
| "train_loss": 0.20370503381276742, |
| "train_runtime": 1178.0684, |
| "train_samples_per_second": 0.509, |
| "train_steps_per_second": 0.033 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 39, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 88667793129472.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
