| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 325, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 1.6880494356155396, | |
| "learning_rate": 1.9384615384615386e-05, | |
| "loss": 1.0254, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 1.6863218545913696, | |
| "learning_rate": 1.876923076923077e-05, | |
| "loss": 0.875, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 1.5608391761779785, | |
| "learning_rate": 1.8153846153846155e-05, | |
| "loss": 0.7825, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.4615881443023682, | |
| "learning_rate": 1.753846153846154e-05, | |
| "loss": 0.6326, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 2.1352627277374268, | |
| "learning_rate": 1.6923076923076924e-05, | |
| "loss": 0.5693, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 1.560471773147583, | |
| "learning_rate": 1.630769230769231e-05, | |
| "loss": 0.4709, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0769230769230769, | |
| "grad_norm": 1.3950369358062744, | |
| "learning_rate": 1.5692307692307693e-05, | |
| "loss": 0.4044, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 1.1524418592453003, | |
| "learning_rate": 1.5076923076923078e-05, | |
| "loss": 0.3491, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3846153846153846, | |
| "grad_norm": 1.3851335048675537, | |
| "learning_rate": 1.4461538461538462e-05, | |
| "loss": 0.3191, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 0.7817617654800415, | |
| "learning_rate": 1.3846153846153847e-05, | |
| "loss": 0.2975, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6923076923076923, | |
| "grad_norm": 2.4296486377716064, | |
| "learning_rate": 1.3230769230769231e-05, | |
| "loss": 0.2719, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 3.495382308959961, | |
| "learning_rate": 1.2615384615384616e-05, | |
| "loss": 0.2863, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.9178031086921692, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.2066, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.1538461538461537, | |
| "grad_norm": 1.042531967163086, | |
| "learning_rate": 1.1384615384615385e-05, | |
| "loss": 0.1934, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.3076923076923075, | |
| "grad_norm": 2.2865443229675293, | |
| "learning_rate": 1.076923076923077e-05, | |
| "loss": 0.1905, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.4615384615384617, | |
| "grad_norm": 2.3291144371032715, | |
| "learning_rate": 1.0153846153846154e-05, | |
| "loss": 0.2134, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.6153846153846154, | |
| "grad_norm": 1.420284628868103, | |
| "learning_rate": 9.53846153846154e-06, | |
| "loss": 0.1895, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.769230769230769, | |
| "grad_norm": 2.7554662227630615, | |
| "learning_rate": 8.923076923076925e-06, | |
| "loss": 0.1897, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.9230769230769234, | |
| "grad_norm": 1.4687916040420532, | |
| "learning_rate": 8.307692307692309e-06, | |
| "loss": 0.1761, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 3.535647392272949, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.1862, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.230769230769231, | |
| "grad_norm": 3.035341739654541, | |
| "learning_rate": 7.076923076923078e-06, | |
| "loss": 0.1937, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.3846153846153846, | |
| "grad_norm": 2.828181028366089, | |
| "learning_rate": 6.461538461538463e-06, | |
| "loss": 0.1407, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.5384615384615383, | |
| "grad_norm": 2.125542163848877, | |
| "learning_rate": 5.846153846153847e-06, | |
| "loss": 0.1338, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.6923076923076925, | |
| "grad_norm": 1.5795857906341553, | |
| "learning_rate": 5.230769230769232e-06, | |
| "loss": 0.131, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.8461538461538463, | |
| "grad_norm": 0.5753270387649536, | |
| "learning_rate": 4.615384615384616e-06, | |
| "loss": 0.1493, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.9189938306808472, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1489, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.153846153846154, | |
| "grad_norm": 0.939368724822998, | |
| "learning_rate": 3.384615384615385e-06, | |
| "loss": 0.1615, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.3076923076923075, | |
| "grad_norm": 1.0938255786895752, | |
| "learning_rate": 2.7692307692307697e-06, | |
| "loss": 0.1433, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.461538461538462, | |
| "grad_norm": 0.398496150970459, | |
| "learning_rate": 2.153846153846154e-06, | |
| "loss": 0.1485, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 1.6919806003570557, | |
| "learning_rate": 1.5384615384615387e-06, | |
| "loss": 0.131, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.769230769230769, | |
| "grad_norm": 0.9723582863807678, | |
| "learning_rate": 9.230769230769232e-07, | |
| "loss": 0.1288, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.923076923076923, | |
| "grad_norm": 0.5153496265411377, | |
| "learning_rate": 3.0769230769230774e-07, | |
| "loss": 0.109, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 325, | |
| "total_flos": 4.006371770595533e+17, | |
| "train_loss": 0.29627929100623496, | |
| "train_runtime": 105.6493, | |
| "train_samples_per_second": 48.935, | |
| "train_steps_per_second": 3.076 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 325, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 4.006371770595533e+17, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |