| { |
| "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": 10.4375, |
| "learning_rate": 4.95e-06, |
| "loss": 1.9152, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1, |
| "grad_norm": 12.75, |
| "learning_rate": 4.9665802678220655e-06, |
| "loss": 1.7984, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.1, |
| "eval_loss": 1.7956634759902954, |
| "eval_runtime": 13.2379, |
| "eval_samples_per_second": 29.234, |
| "eval_steps_per_second": 7.327, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.15, |
| "grad_norm": 9.75, |
| "learning_rate": 4.865882073285087e-06, |
| "loss": 1.7592, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.2, |
| "grad_norm": 9.5, |
| "learning_rate": 4.700648783183159e-06, |
| "loss": 1.74, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.2, |
| "eval_loss": 1.7555052042007446, |
| "eval_runtime": 13.2827, |
| "eval_samples_per_second": 29.136, |
| "eval_steps_per_second": 7.303, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.25, |
| "grad_norm": 10.625, |
| "learning_rate": 4.475387530939226e-06, |
| "loss": 1.7321, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.3, |
| "grad_norm": 9.75, |
| "learning_rate": 4.196242856302242e-06, |
| "loss": 1.7098, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.3, |
| "eval_loss": 1.7369353771209717, |
| "eval_runtime": 13.2636, |
| "eval_samples_per_second": 29.178, |
| "eval_steps_per_second": 7.313, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.35, |
| "grad_norm": 10.4375, |
| "learning_rate": 3.870829098320446e-06, |
| "loss": 1.7146, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 8.875, |
| "learning_rate": 3.508022696021226e-06, |
| "loss": 1.7045, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.4, |
| "eval_loss": 1.7258087396621704, |
| "eval_runtime": 13.7692, |
| "eval_samples_per_second": 28.106, |
| "eval_steps_per_second": 7.045, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.45, |
| "grad_norm": 8.625, |
| "learning_rate": 3.1177200622935994e-06, |
| "loss": 1.6859, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.5, |
| "grad_norm": 9.125, |
| "learning_rate": 2.7105676355426245e-06, |
| "loss": 1.6995, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5, |
| "eval_loss": 1.7192906141281128, |
| "eval_runtime": 13.917, |
| "eval_samples_per_second": 27.808, |
| "eval_steps_per_second": 6.97, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.55, |
| "grad_norm": 9.5, |
| "learning_rate": 2.297671472602907e-06, |
| "loss": 1.6852, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.6, |
| "grad_norm": 10.3125, |
| "learning_rate": 1.8902943044594735e-06, |
| "loss": 1.6776, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.6, |
| "eval_loss": 1.7203726768493652, |
| "eval_runtime": 13.9092, |
| "eval_samples_per_second": 27.823, |
| "eval_steps_per_second": 6.974, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.65, |
| "grad_norm": 9.625, |
| "learning_rate": 1.4995483183062589e-06, |
| "loss": 1.6684, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.7, |
| "grad_norm": 9.8125, |
| "learning_rate": 1.1360920460467598e-06, |
| "loss": 1.676, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.7, |
| "eval_loss": 1.7204886674880981, |
| "eval_runtime": 13.9562, |
| "eval_samples_per_second": 27.73, |
| "eval_steps_per_second": 6.95, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.75, |
| "grad_norm": 10.875, |
| "learning_rate": 8.098396273284237e-07, |
| "loss": 1.689, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 10.5625, |
| "learning_rate": 5.296903776573065e-07, |
| "loss": 1.6798, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 1.7192721366882324, |
| "eval_runtime": 13.9557, |
| "eval_samples_per_second": 27.731, |
| "eval_steps_per_second": 6.951, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.85, |
| "grad_norm": 10.25, |
| "learning_rate": 3.032860382698466e-07, |
| "loss": 1.682, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.9, |
| "grad_norm": 9.4375, |
| "learning_rate": 1.368023293524695e-07, |
| "loss": 1.6811, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.9, |
| "eval_loss": 1.720568299293518, |
| "eval_runtime": 13.5977, |
| "eval_samples_per_second": 28.461, |
| "eval_steps_per_second": 7.134, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.95, |
| "grad_norm": 9.8125, |
| "learning_rate": 3.478049249380194e-08, |
| "loss": 1.6978, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 9.25, |
| "learning_rate": 3.4174522689500723e-12, |
| "loss": 1.6742, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 1.7223052978515625, |
| "eval_runtime": 13.8584, |
| "eval_samples_per_second": 27.925, |
| "eval_steps_per_second": 6.999, |
| "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 |
| } |
|
|
