| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.027816411682892908, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0027816411682892906, | |
| "grad_norm": 0.008169702254235744, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9375, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027816411682892906, | |
| "eval_loss": 11.932051658630371, | |
| "eval_runtime": 0.8302, | |
| "eval_samples_per_second": 183.094, | |
| "eval_steps_per_second": 91.547, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005563282336578581, | |
| "grad_norm": 0.004439120646566153, | |
| "learning_rate": 4e-05, | |
| "loss": 11.932, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008344923504867872, | |
| "grad_norm": 0.006543128285557032, | |
| "learning_rate": 6e-05, | |
| "loss": 11.9333, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.008344923504867872, | |
| "eval_loss": 11.932050704956055, | |
| "eval_runtime": 0.8212, | |
| "eval_samples_per_second": 185.09, | |
| "eval_steps_per_second": 92.545, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011126564673157162, | |
| "grad_norm": 0.006569739896804094, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9374, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013908205841446454, | |
| "grad_norm": 0.005256724078208208, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9328, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.016689847009735744, | |
| "grad_norm": 0.009198017418384552, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9323, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.016689847009735744, | |
| "eval_loss": 11.932042121887207, | |
| "eval_runtime": 0.8366, | |
| "eval_samples_per_second": 181.685, | |
| "eval_steps_per_second": 90.843, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019471488178025034, | |
| "grad_norm": 0.006066080182790756, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9294, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.022253129346314324, | |
| "grad_norm": 0.008948218077421188, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9354, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.025034770514603615, | |
| "grad_norm": 0.007288319058716297, | |
| "learning_rate": 0.00018, | |
| "loss": 11.935, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025034770514603615, | |
| "eval_loss": 11.932028770446777, | |
| "eval_runtime": 0.8261, | |
| "eval_samples_per_second": 183.991, | |
| "eval_steps_per_second": 91.995, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027816411682892908, | |
| "grad_norm": 0.0041886246763169765, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9275, | |
| "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": 2215526400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |