| { |
| "best_global_step": 1000, |
| "best_metric": 4.908256232738495e-05, |
| "best_model_checkpoint": "/data/repository_library/models/checkpoints/A1/checkpoint-1000", |
| "epoch": 0.08861320336730173, |
| "eval_steps": 200, |
| "global_step": 1000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.004430660168365086, |
| "grad_norm": 0.12783098220825195, |
| "learning_rate": 4.9000000000000005e-06, |
| "loss": 0.0345, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.008861320336730172, |
| "grad_norm": 0.09784713387489319, |
| "learning_rate": 9.900000000000002e-06, |
| "loss": 0.0255, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.01329198050509526, |
| "grad_norm": 0.05850409343838692, |
| "learning_rate": 1.49e-05, |
| "loss": 0.0157, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.017722640673460344, |
| "grad_norm": 0.04804951325058937, |
| "learning_rate": 1.9900000000000003e-05, |
| "loss": 0.0133, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.017722640673460344, |
| "eval_loss": 0.006413444876670837, |
| "eval_runtime": 77.8113, |
| "eval_samples_per_second": 3.29, |
| "eval_steps_per_second": 3.29, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.022153300841825433, |
| "grad_norm": 0.03711477667093277, |
| "learning_rate": 2.4900000000000002e-05, |
| "loss": 0.0056, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.02658396101019052, |
| "grad_norm": 0.01747751049697399, |
| "learning_rate": 2.9900000000000002e-05, |
| "loss": 0.0031, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.031014621178555603, |
| "grad_norm": 0.008964906446635723, |
| "learning_rate": 3.49e-05, |
| "loss": 0.0016, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.03544528134692069, |
| "grad_norm": 0.0075602042488753796, |
| "learning_rate": 3.99e-05, |
| "loss": 0.005, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.03544528134692069, |
| "eval_loss": 0.000701970187947154, |
| "eval_runtime": 77.3052, |
| "eval_samples_per_second": 3.312, |
| "eval_steps_per_second": 3.312, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.03987594151528578, |
| "grad_norm": 0.006457478739321232, |
| "learning_rate": 4.49e-05, |
| "loss": 0.0007, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.044306601683650866, |
| "grad_norm": 0.0036411744076758623, |
| "learning_rate": 4.99e-05, |
| "loss": 0.0125, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.04873726185201595, |
| "grad_norm": 0.00494934618473053, |
| "learning_rate": 5.4900000000000006e-05, |
| "loss": 0.0084, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.05316792202038104, |
| "grad_norm": 0.0022771055810153484, |
| "learning_rate": 5.99e-05, |
| "loss": 0.0003, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.05316792202038104, |
| "eval_loss": 0.0002107138279825449, |
| "eval_runtime": 76.9791, |
| "eval_samples_per_second": 3.326, |
| "eval_steps_per_second": 3.326, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.057598582188746125, |
| "grad_norm": 0.0016827695071697235, |
| "learning_rate": 6.49e-05, |
| "loss": 0.0042, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.06202924235711121, |
| "grad_norm": 0.0017612947849556804, |
| "learning_rate": 6.99e-05, |
| "loss": 0.0042, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.0664599025254763, |
| "grad_norm": 0.0027868652250617743, |
| "learning_rate": 7.49e-05, |
| "loss": 0.0002, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.07089056269384138, |
| "grad_norm": 0.0012559776660054922, |
| "learning_rate": 7.99e-05, |
| "loss": 0.0081, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.07089056269384138, |
| "eval_loss": 9.173620492219925e-05, |
| "eval_runtime": 78.6347, |
| "eval_samples_per_second": 3.256, |
| "eval_steps_per_second": 3.256, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.07532122286220647, |
| "grad_norm": 0.0010207054438069463, |
| "learning_rate": 8.49e-05, |
| "loss": 0.0001, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.07975188303057155, |
| "grad_norm": 0.0005506079760380089, |
| "learning_rate": 8.99e-05, |
| "loss": 0.0041, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.08418254319893664, |
| "grad_norm": 0.0009705860284157097, |
| "learning_rate": 9.49e-05, |
| "loss": 0.0081, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.08861320336730173, |
| "grad_norm": 0.0012878917623311281, |
| "learning_rate": 9.99e-05, |
| "loss": 0.0121, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.08861320336730173, |
| "eval_loss": 4.908256232738495e-05, |
| "eval_runtime": 79.0738, |
| "eval_samples_per_second": 3.237, |
| "eval_steps_per_second": 3.237, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.08861320336730173, |
| "step": 1000, |
| "total_flos": 0.0, |
| "train_loss": 0.008355697497725486, |
| "train_runtime": 3433.1681, |
| "train_samples_per_second": 1.165, |
| "train_steps_per_second": 0.291 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
