| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.24509803921568626, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0024509803921568627, | |
| "eval_loss": 12.454689025878906, | |
| "eval_runtime": 5.6213, | |
| "eval_samples_per_second": 122.392, | |
| "eval_steps_per_second": 15.299, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007352941176470588, | |
| "grad_norm": 0.008854148909449577, | |
| "learning_rate": 3e-05, | |
| "loss": 12.4564, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014705882352941176, | |
| "grad_norm": 0.009888158179819584, | |
| "learning_rate": 6e-05, | |
| "loss": 12.4569, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022058823529411766, | |
| "grad_norm": 0.007828481495380402, | |
| "learning_rate": 9e-05, | |
| "loss": 12.4527, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022058823529411766, | |
| "eval_loss": 12.454665184020996, | |
| "eval_runtime": 5.6464, | |
| "eval_samples_per_second": 121.848, | |
| "eval_steps_per_second": 15.231, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.029411764705882353, | |
| "grad_norm": 0.0062802694737911224, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 12.459, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03676470588235294, | |
| "grad_norm": 0.008460123091936111, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 12.4535, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04411764705882353, | |
| "grad_norm": 0.008190251886844635, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 12.4544, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04411764705882353, | |
| "eval_loss": 12.454602241516113, | |
| "eval_runtime": 5.6416, | |
| "eval_samples_per_second": 121.952, | |
| "eval_steps_per_second": 15.244, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.051470588235294115, | |
| "grad_norm": 0.008424337953329086, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 12.4507, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.058823529411764705, | |
| "grad_norm": 0.009385749697685242, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 12.457, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0661764705882353, | |
| "grad_norm": 0.0088015366345644, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 12.4589, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0661764705882353, | |
| "eval_loss": 12.454548835754395, | |
| "eval_runtime": 5.6402, | |
| "eval_samples_per_second": 121.982, | |
| "eval_steps_per_second": 15.248, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07352941176470588, | |
| "grad_norm": 0.009232423268258572, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 12.4546, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08088235294117647, | |
| "grad_norm": 0.008932845667004585, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 12.4569, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.08823529411764706, | |
| "grad_norm": 0.008380930870771408, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 12.4534, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.08823529411764706, | |
| "eval_loss": 12.454479217529297, | |
| "eval_runtime": 5.6394, | |
| "eval_samples_per_second": 122.0, | |
| "eval_steps_per_second": 15.25, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.09558823529411764, | |
| "grad_norm": 0.007541842758655548, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 12.4577, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.10294117647058823, | |
| "grad_norm": 0.009072437882423401, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 12.4512, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11029411764705882, | |
| "grad_norm": 0.00889171939343214, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 12.4593, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11029411764705882, | |
| "eval_loss": 12.454415321350098, | |
| "eval_runtime": 5.6364, | |
| "eval_samples_per_second": 122.063, | |
| "eval_steps_per_second": 15.258, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 0.011012999340891838, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 12.4561, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 0.00962892733514309, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 12.4539, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1323529411764706, | |
| "grad_norm": 0.00907512754201889, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 12.4555, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1323529411764706, | |
| "eval_loss": 12.454337120056152, | |
| "eval_runtime": 5.6351, | |
| "eval_samples_per_second": 122.091, | |
| "eval_steps_per_second": 15.261, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.13970588235294118, | |
| "grad_norm": 0.009578227065503597, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 12.456, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.14705882352941177, | |
| "grad_norm": 0.009201650507748127, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 12.4541, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15441176470588236, | |
| "grad_norm": 0.01162680983543396, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 12.4568, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.15441176470588236, | |
| "eval_loss": 12.454294204711914, | |
| "eval_runtime": 5.6362, | |
| "eval_samples_per_second": 122.067, | |
| "eval_steps_per_second": 15.258, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.16176470588235295, | |
| "grad_norm": 0.009980561211705208, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 12.4532, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.16911764705882354, | |
| "grad_norm": 0.009362083859741688, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 12.4559, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.17647058823529413, | |
| "grad_norm": 0.012317374348640442, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 12.4575, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.17647058823529413, | |
| "eval_loss": 12.454255104064941, | |
| "eval_runtime": 5.6442, | |
| "eval_samples_per_second": 121.896, | |
| "eval_steps_per_second": 15.237, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.18382352941176472, | |
| "grad_norm": 0.009673560969531536, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 12.4546, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.19117647058823528, | |
| "grad_norm": 0.009031685069203377, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 12.4564, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.19852941176470587, | |
| "grad_norm": 0.012030497193336487, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 12.4545, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.19852941176470587, | |
| "eval_loss": 12.454232215881348, | |
| "eval_runtime": 5.6389, | |
| "eval_samples_per_second": 122.01, | |
| "eval_steps_per_second": 15.251, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.20588235294117646, | |
| "grad_norm": 0.013549219816923141, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 12.455, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.21323529411764705, | |
| "grad_norm": 0.011278319172561169, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 12.4558, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.22058823529411764, | |
| "grad_norm": 0.009173925966024399, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 12.4548, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22058823529411764, | |
| "eval_loss": 12.4542236328125, | |
| "eval_runtime": 5.6365, | |
| "eval_samples_per_second": 122.062, | |
| "eval_steps_per_second": 15.258, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22794117647058823, | |
| "grad_norm": 0.010029138065874577, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 12.4577, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.009600088000297546, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 12.4516, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.2426470588235294, | |
| "grad_norm": 0.01012326404452324, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 12.4586, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2426470588235294, | |
| "eval_loss": 12.45422077178955, | |
| "eval_runtime": 5.6384, | |
| "eval_samples_per_second": 122.021, | |
| "eval_steps_per_second": 15.253, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 123312537600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |