| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004664342269435731, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.328684538871463e-05, | |
| "eval_loss": 6.389310836791992, | |
| "eval_runtime": 1171.7578, | |
| "eval_samples_per_second": 15.408, | |
| "eval_steps_per_second": 3.852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027986053616614387, | |
| "grad_norm": 8.369600296020508, | |
| "learning_rate": 3e-05, | |
| "loss": 6.0336, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00046643422694357315, | |
| "eval_loss": 4.579810619354248, | |
| "eval_runtime": 1127.02, | |
| "eval_samples_per_second": 16.02, | |
| "eval_steps_per_second": 4.005, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005597210723322877, | |
| "grad_norm": 5.414619445800781, | |
| "learning_rate": 6e-05, | |
| "loss": 5.0959, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008395816084984316, | |
| "grad_norm": 3.53025484085083, | |
| "learning_rate": 9e-05, | |
| "loss": 3.4984, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009328684538871463, | |
| "eval_loss": 2.2199866771698, | |
| "eval_runtime": 1127.2384, | |
| "eval_samples_per_second": 16.017, | |
| "eval_steps_per_second": 4.004, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011194421446645755, | |
| "grad_norm": 3.462336540222168, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 2.315, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0013993026808307193, | |
| "grad_norm": 3.0801501274108887, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5734, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013993026808307193, | |
| "eval_loss": 1.2294880151748657, | |
| "eval_runtime": 1127.2145, | |
| "eval_samples_per_second": 16.017, | |
| "eval_steps_per_second": 4.005, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0016791632169968632, | |
| "grad_norm": 2.642324209213257, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.1533, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0018657369077742926, | |
| "eval_loss": 1.0050814151763916, | |
| "eval_runtime": 1127.5321, | |
| "eval_samples_per_second": 16.013, | |
| "eval_steps_per_second": 4.003, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001959023753163007, | |
| "grad_norm": 3.2567591667175293, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 1.0721, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.002238884289329151, | |
| "grad_norm": 2.1846158504486084, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.9161, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0023321711347178654, | |
| "eval_loss": 0.9646629691123962, | |
| "eval_runtime": 1127.0671, | |
| "eval_samples_per_second": 16.019, | |
| "eval_steps_per_second": 4.005, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.002518744825495295, | |
| "grad_norm": 3.0833184719085693, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 1.0283, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0027986053616614387, | |
| "grad_norm": 2.3142240047454834, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8235, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0027986053616614387, | |
| "eval_loss": 0.9399139285087585, | |
| "eval_runtime": 1126.7479, | |
| "eval_samples_per_second": 16.024, | |
| "eval_steps_per_second": 4.006, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0030784658978275825, | |
| "grad_norm": 1.7494417428970337, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 1.0393, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.003265039588605012, | |
| "eval_loss": 0.9136942625045776, | |
| "eval_runtime": 1127.0527, | |
| "eval_samples_per_second": 16.02, | |
| "eval_steps_per_second": 4.005, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0033583264339937264, | |
| "grad_norm": 1.945104718208313, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.8866, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0036381869701598703, | |
| "grad_norm": 2.1890666484832764, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.8145, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.003731473815548585, | |
| "eval_loss": 0.9032037258148193, | |
| "eval_runtime": 1127.1057, | |
| "eval_samples_per_second": 16.019, | |
| "eval_steps_per_second": 4.005, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.003918047506326014, | |
| "grad_norm": 1.5312135219573975, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.8295, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.004197908042492158, | |
| "grad_norm": 1.5169057846069336, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9098, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004197908042492158, | |
| "eval_loss": 0.8880054950714111, | |
| "eval_runtime": 1127.4078, | |
| "eval_samples_per_second": 16.015, | |
| "eval_steps_per_second": 4.004, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.004477768578658302, | |
| "grad_norm": 1.6393113136291504, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.7374, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.004664342269435731, | |
| "eval_loss": 0.8864649534225464, | |
| "eval_runtime": 1127.3926, | |
| "eval_samples_per_second": 16.015, | |
| "eval_steps_per_second": 4.004, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.051913716989952e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |