| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 200, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.05, |
| "grad_norm": 10.3125, |
| "learning_rate": 4.95e-06, |
| "loss": 1.8485, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 8.875, |
| "learning_rate": 4.9665802678220655e-06, |
| "loss": 1.7113, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_loss": 1.6866151094436646, |
| "eval_runtime": 11.4804, |
| "eval_samples_per_second": 29.006, |
| "eval_steps_per_second": 7.317, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 12.75, |
| "learning_rate": 4.865882073285087e-06, |
| "loss": 1.6597, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 9.875, |
| "learning_rate": 4.700648783183159e-06, |
| "loss": 1.631, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 1.6420836448669434, |
| "eval_runtime": 11.3252, |
| "eval_samples_per_second": 29.404, |
| "eval_steps_per_second": 7.417, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 8.9375, |
| "learning_rate": 4.475387530939226e-06, |
| "loss": 1.6129, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 9.3125, |
| "learning_rate": 4.196242856302242e-06, |
| "loss": 1.5943, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3, |
| "eval_loss": 1.619098424911499, |
| "eval_runtime": 11.4305, |
| "eval_samples_per_second": 29.133, |
| "eval_steps_per_second": 7.349, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 10.3125, |
| "learning_rate": 3.870829098320446e-06, |
| "loss": 1.5993, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 9.125, |
| "learning_rate": 3.508022696021226e-06, |
| "loss": 1.5879, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 1.6125136613845825, |
| "eval_runtime": 12.0057, |
| "eval_samples_per_second": 27.737, |
| "eval_steps_per_second": 6.997, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 9.9375, |
| "learning_rate": 3.1177200622935994e-06, |
| "loss": 1.5779, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 10.25, |
| "learning_rate": 2.7105676355426245e-06, |
| "loss": 1.5674, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 1.6076483726501465, |
| "eval_runtime": 11.4085, |
| "eval_samples_per_second": 29.189, |
| "eval_steps_per_second": 7.363, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 9.1875, |
| "learning_rate": 2.297671472602907e-06, |
| "loss": 1.5764, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 10.9375, |
| "learning_rate": 1.8902943044594735e-06, |
| "loss": 1.5605, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_loss": 1.608046531677246, |
| "eval_runtime": 11.8944, |
| "eval_samples_per_second": 27.996, |
| "eval_steps_per_second": 7.062, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 11.1875, |
| "learning_rate": 1.4995483183062589e-06, |
| "loss": 1.5642, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 8.5625, |
| "learning_rate": 1.1360920460467598e-06, |
| "loss": 1.5669, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.7, |
| "eval_loss": 1.605462908744812, |
| "eval_runtime": 11.4089, |
| "eval_samples_per_second": 29.188, |
| "eval_steps_per_second": 7.363, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 10.25, |
| "learning_rate": 8.098396273284237e-07, |
| "loss": 1.5647, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 9.6875, |
| "learning_rate": 5.296903776573065e-07, |
| "loss": 1.5747, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 1.60719895362854, |
| "eval_runtime": 11.7482, |
| "eval_samples_per_second": 28.345, |
| "eval_steps_per_second": 7.15, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 10.0625, |
| "learning_rate": 3.032860382698466e-07, |
| "loss": 1.5597, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 11.0625, |
| "learning_rate": 1.368023293524695e-07, |
| "loss": 1.5693, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.9, |
| "eval_loss": 1.6088706254959106, |
| "eval_runtime": 11.8628, |
| "eval_samples_per_second": 28.071, |
| "eval_steps_per_second": 7.081, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 9.9375, |
| "learning_rate": 3.478049249380194e-08, |
| "loss": 1.57, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 9.5, |
| "learning_rate": 3.4174522689500723e-12, |
| "loss": 1.5596, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.6078001260757446, |
| "eval_runtime": 11.6304, |
| "eval_samples_per_second": 28.632, |
| "eval_steps_per_second": 7.222, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 2000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "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": 1.40731264008192e+17, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
