| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022913881993507735, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007637960664502578, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.434, | |
| "eval_samples_per_second": 25.753, | |
| "eval_steps_per_second": 12.877, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022913881993507734, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003818980332251289, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.0662, | |
| "eval_samples_per_second": 26.203, | |
| "eval_steps_per_second": 13.102, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004582776398701547, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00687416459805232, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007637960664502578, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.0841, | |
| "eval_samples_per_second": 26.181, | |
| "eval_steps_per_second": 13.09, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009165552797403094, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011456940996753867, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011456940996753867, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.0271, | |
| "eval_samples_per_second": 26.252, | |
| "eval_steps_per_second": 13.126, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01374832919610464, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015275921329005156, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.0164, | |
| "eval_samples_per_second": 26.265, | |
| "eval_steps_per_second": 13.133, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.016039717395455413, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018331105594806187, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.019094901661256443, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.0098, | |
| "eval_samples_per_second": 26.273, | |
| "eval_steps_per_second": 13.137, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02062249379415696, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.022913881993507735, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.022913881993507735, | |
| "eval_loss": NaN, | |
| "eval_runtime": 21.0229, | |
| "eval_samples_per_second": 26.257, | |
| "eval_steps_per_second": 13.129, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2742014856658944.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |