| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002052629418284823, | |
| "eval_steps": 9, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.210517673139291e-05, | |
| "grad_norm": 1.3583542108535767, | |
| "learning_rate": 1e-05, | |
| "loss": 1.8764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.210517673139291e-05, | |
| "eval_loss": 2.0353238582611084, | |
| "eval_runtime": 1410.7367, | |
| "eval_samples_per_second": 7.271, | |
| "eval_steps_per_second": 0.909, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016421035346278582, | |
| "grad_norm": 0.9403209686279297, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2456, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00024631553019417875, | |
| "grad_norm": 1.0389089584350586, | |
| "learning_rate": 3e-05, | |
| "loss": 2.1613, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00032842070692557163, | |
| "grad_norm": 1.2952375411987305, | |
| "learning_rate": 4e-05, | |
| "loss": 2.067, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00041052588365696457, | |
| "grad_norm": 1.1285730600357056, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0318, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004926310603883575, | |
| "grad_norm": 1.138143539428711, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9186, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005747362371197504, | |
| "grad_norm": 1.3923189640045166, | |
| "learning_rate": 7e-05, | |
| "loss": 2.0116, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006568414138511433, | |
| "grad_norm": 1.3150489330291748, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9182, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007389465905825362, | |
| "grad_norm": 1.29096257686615, | |
| "learning_rate": 9e-05, | |
| "loss": 1.7837, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007389465905825362, | |
| "eval_loss": 1.8958570957183838, | |
| "eval_runtime": 1414.3183, | |
| "eval_samples_per_second": 7.252, | |
| "eval_steps_per_second": 0.907, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008210517673139291, | |
| "grad_norm": 1.190146565437317, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8945, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009031569440453221, | |
| "grad_norm": 1.033207654953003, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 1.5682, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000985262120776715, | |
| "grad_norm": 1.2630507946014404, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.9524, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0010673672975081078, | |
| "grad_norm": 0.8601189255714417, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 1.7826, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0011494724742395009, | |
| "grad_norm": 0.6138840913772583, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 1.9201, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0012315776509708937, | |
| "grad_norm": 0.9678861498832703, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 1.6454, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0013136828277022865, | |
| "grad_norm": 0.8818705677986145, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 1.9118, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0013957880044336796, | |
| "grad_norm": 0.8292626738548279, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.8557, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0014778931811650724, | |
| "grad_norm": 0.7435213327407837, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 1.7706, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0014778931811650724, | |
| "eval_loss": 1.6920524835586548, | |
| "eval_runtime": 1413.5511, | |
| "eval_samples_per_second": 7.256, | |
| "eval_steps_per_second": 0.908, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0015599983578964654, | |
| "grad_norm": 0.964107096195221, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.3101, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0016421035346278583, | |
| "grad_norm": 0.7826007008552551, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 1.6482, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.001724208711359251, | |
| "grad_norm": 0.8321696519851685, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.825, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0018063138880906441, | |
| "grad_norm": 1.1344892978668213, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 1.091, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.001888419064822037, | |
| "grad_norm": 0.885356605052948, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.5937, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00197052424155343, | |
| "grad_norm": 1.1985459327697754, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 1.5686, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002052629418284823, | |
| "grad_norm": 0.807948648929596, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.194, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.299850579037389e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |