| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.011560693641618497, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0011560693641618498, | |
| "grad_norm": 10.487594604492188, | |
| "learning_rate": 2e-05, | |
| "loss": 18.8725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011560693641618498, | |
| "eval_loss": 4.957520008087158, | |
| "eval_runtime": 11.4304, | |
| "eval_samples_per_second": 31.932, | |
| "eval_steps_per_second": 16.01, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0023121387283236996, | |
| "grad_norm": 6.101963520050049, | |
| "learning_rate": 4e-05, | |
| "loss": 18.8102, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003468208092485549, | |
| "grad_norm": 6.275629997253418, | |
| "learning_rate": 6e-05, | |
| "loss": 20.8583, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003468208092485549, | |
| "eval_loss": 4.9551100730896, | |
| "eval_runtime": 10.2288, | |
| "eval_samples_per_second": 35.684, | |
| "eval_steps_per_second": 17.891, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004624277456647399, | |
| "grad_norm": 6.729939937591553, | |
| "learning_rate": 8e-05, | |
| "loss": 22.5133, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.005780346820809248, | |
| "grad_norm": 6.627227783203125, | |
| "learning_rate": 0.0001, | |
| "loss": 16.5759, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006936416184971098, | |
| "grad_norm": 9.372757911682129, | |
| "learning_rate": 0.00012, | |
| "loss": 20.9193, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006936416184971098, | |
| "eval_loss": 4.744518756866455, | |
| "eval_runtime": 10.2094, | |
| "eval_samples_per_second": 35.751, | |
| "eval_steps_per_second": 17.925, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008092485549132947, | |
| "grad_norm": 8.81309986114502, | |
| "learning_rate": 0.00014, | |
| "loss": 15.7233, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.009248554913294798, | |
| "grad_norm": 13.7530517578125, | |
| "learning_rate": 0.00016, | |
| "loss": 18.5885, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.010404624277456647, | |
| "grad_norm": 26.067075729370117, | |
| "learning_rate": 0.00018, | |
| "loss": 18.9052, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010404624277456647, | |
| "eval_loss": 3.526338815689087, | |
| "eval_runtime": 10.2913, | |
| "eval_samples_per_second": 35.467, | |
| "eval_steps_per_second": 17.782, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.011560693641618497, | |
| "grad_norm": 16.398164749145508, | |
| "learning_rate": 0.0002, | |
| "loss": 12.7587, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1632478030725120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |