| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.03076804738279297, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0015384023691396484, |
| "grad_norm": 15216.6796875, |
| "learning_rate": 1.9999999999999996e-07, |
| "loss": 7.628, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.003076804738279297, |
| "grad_norm": 539.3572387695312, |
| "learning_rate": 1.2e-06, |
| "loss": 7.3644, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.004615207107418946, |
| "grad_norm": 496.3940734863281, |
| "learning_rate": 2.1999999999999997e-06, |
| "loss": 7.0137, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.006153609476558594, |
| "grad_norm": 110.5931396484375, |
| "learning_rate": 3.1999999999999994e-06, |
| "loss": 6.9299, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.007692011845698243, |
| "grad_norm": 442.7750549316406, |
| "learning_rate": 4.2e-06, |
| "loss": 6.88, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.009230414214837892, |
| "grad_norm": 285.75390625, |
| "learning_rate": 5.199999999999999e-06, |
| "loss": 6.7252, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.010768816583977539, |
| "grad_norm": 238.201416015625, |
| "learning_rate": 6.199999999999999e-06, |
| "loss": 6.7641, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.012307218953117188, |
| "grad_norm": 203.7633514404297, |
| "learning_rate": 7.2e-06, |
| "loss": 6.6961, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.013845621322256836, |
| "grad_norm": 537.8616943359375, |
| "learning_rate": 8.2e-06, |
| "loss": 6.5996, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.015384023691396485, |
| "grad_norm": 643.6299438476562, |
| "learning_rate": 9.199999999999998e-06, |
| "loss": 6.5856, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.016922426060536132, |
| "grad_norm": 679.996337890625, |
| "learning_rate": 1.02e-05, |
| "loss": 6.599, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.018460828429675783, |
| "grad_norm": 452.3795471191406, |
| "learning_rate": 1.12e-05, |
| "loss": 6.6354, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.01999923079881543, |
| "grad_norm": 117.24376678466797, |
| "learning_rate": 1.2199999999999998e-05, |
| "loss": 6.5363, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.021537633167955077, |
| "grad_norm": 145.65036010742188, |
| "learning_rate": 1.3199999999999997e-05, |
| "loss": 6.5564, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.023076035537094728, |
| "grad_norm": 178.4263458251953, |
| "learning_rate": 1.4199999999999998e-05, |
| "loss": 6.5828, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.024614437906234375, |
| "grad_norm": 174.7183837890625, |
| "learning_rate": 1.5199999999999998e-05, |
| "loss": 6.4821, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.026152840275374026, |
| "grad_norm": 145.78704833984375, |
| "learning_rate": 1.6199999999999997e-05, |
| "loss": 6.4711, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.027691242644513673, |
| "grad_norm": 217.81866455078125, |
| "learning_rate": 1.7199999999999998e-05, |
| "loss": 6.4947, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.02922964501365332, |
| "grad_norm": 105.79635620117188, |
| "learning_rate": 1.82e-05, |
| "loss": 6.4997, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.03076804738279297, |
| "grad_norm": 86.61837768554688, |
| "learning_rate": 1.92e-05, |
| "loss": 6.4604, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 100000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 16, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3826920846950400.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
