| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.128205128205128, | |
| "eval_steps": 100, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 81.8341293334961, | |
| "learning_rate": 9.990900000000001e-06, | |
| "loss": 3.5606, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "eval_loss": 2.2667126655578613, | |
| "eval_runtime": 33.7385, | |
| "eval_samples_per_second": 11.648, | |
| "eval_steps_per_second": 1.482, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "grad_norm": 30.16681671142578, | |
| "learning_rate": 9.980900000000001e-06, | |
| "loss": 2.1841, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0256410256410255, | |
| "eval_loss": 2.059685230255127, | |
| "eval_runtime": 33.6897, | |
| "eval_samples_per_second": 11.665, | |
| "eval_steps_per_second": 1.484, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 67.16844177246094, | |
| "learning_rate": 9.970900000000001e-06, | |
| "loss": 2.0949, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "eval_loss": 1.9054155349731445, | |
| "eval_runtime": 33.6472, | |
| "eval_samples_per_second": 11.68, | |
| "eval_steps_per_second": 1.486, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "grad_norm": 46.190330505371094, | |
| "learning_rate": 9.960900000000001e-06, | |
| "loss": 1.9236, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.051282051282051, | |
| "eval_loss": 1.8464823961257935, | |
| "eval_runtime": 33.8143, | |
| "eval_samples_per_second": 11.622, | |
| "eval_steps_per_second": 1.479, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "grad_norm": 42.82326889038086, | |
| "learning_rate": 9.950900000000002e-06, | |
| "loss": 1.937, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.564102564102564, | |
| "eval_loss": 1.8186373710632324, | |
| "eval_runtime": 33.9112, | |
| "eval_samples_per_second": 11.589, | |
| "eval_steps_per_second": 1.474, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "grad_norm": 68.72016906738281, | |
| "learning_rate": 9.940900000000002e-06, | |
| "loss": 1.8648, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.076923076923077, | |
| "eval_loss": 1.7807129621505737, | |
| "eval_runtime": 33.4957, | |
| "eval_samples_per_second": 11.733, | |
| "eval_steps_per_second": 1.493, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 3.58974358974359, | |
| "grad_norm": 51.390071868896484, | |
| "learning_rate": 9.930900000000002e-06, | |
| "loss": 1.8162, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.58974358974359, | |
| "eval_loss": 1.7275961637496948, | |
| "eval_runtime": 33.6095, | |
| "eval_samples_per_second": 11.693, | |
| "eval_steps_per_second": 1.488, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "grad_norm": 33.017948150634766, | |
| "learning_rate": 9.920900000000002e-06, | |
| "loss": 1.7331, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.102564102564102, | |
| "eval_loss": 1.701725959777832, | |
| "eval_runtime": 33.9602, | |
| "eval_samples_per_second": 11.572, | |
| "eval_steps_per_second": 1.472, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "grad_norm": 43.55423355102539, | |
| "learning_rate": 9.9109e-06, | |
| "loss": 1.7091, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.615384615384615, | |
| "eval_loss": 1.6944857835769653, | |
| "eval_runtime": 33.6785, | |
| "eval_samples_per_second": 11.669, | |
| "eval_steps_per_second": 1.485, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 5.128205128205128, | |
| "grad_norm": 67.6618881225586, | |
| "learning_rate": 9.9009e-06, | |
| "loss": 1.7258, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.128205128205128, | |
| "eval_loss": 1.65646493434906, | |
| "eval_runtime": 33.8316, | |
| "eval_samples_per_second": 11.616, | |
| "eval_steps_per_second": 1.478, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 100000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 513, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.82243166208e+18, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |