| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.019062748212867357, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006354249404289118, | |
| "eval_loss": 2.0787065029144287, | |
| "eval_runtime": 45.6753, | |
| "eval_samples_per_second": 14.516, | |
| "eval_steps_per_second": 7.269, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019062748212867356, | |
| "grad_norm": 1.3591597080230713, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0204, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003177124702144559, | |
| "eval_loss": 1.9998044967651367, | |
| "eval_runtime": 46.1079, | |
| "eval_samples_per_second": 14.379, | |
| "eval_steps_per_second": 7.201, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003812549642573471, | |
| "grad_norm": 1.6216338872909546, | |
| "learning_rate": 8e-05, | |
| "loss": 1.9456, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005718824463860206, | |
| "grad_norm": 1.2791810035705566, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7605, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006354249404289118, | |
| "eval_loss": 1.532446026802063, | |
| "eval_runtime": 46.267, | |
| "eval_samples_per_second": 14.33, | |
| "eval_steps_per_second": 7.176, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007625099285146942, | |
| "grad_norm": 1.1944502592086792, | |
| "learning_rate": 0.00016, | |
| "loss": 1.5884, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009531374106433678, | |
| "grad_norm": 1.2674814462661743, | |
| "learning_rate": 0.0002, | |
| "loss": 1.3116, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009531374106433678, | |
| "eval_loss": 1.3473174571990967, | |
| "eval_runtime": 46.3179, | |
| "eval_samples_per_second": 14.314, | |
| "eval_steps_per_second": 7.168, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011437648927720413, | |
| "grad_norm": 1.0547869205474854, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 1.2018, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012708498808578236, | |
| "eval_loss": 1.188161849975586, | |
| "eval_runtime": 46.328, | |
| "eval_samples_per_second": 14.311, | |
| "eval_steps_per_second": 7.166, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013343923749007149, | |
| "grad_norm": 0.924247145652771, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.1364, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.015250198570293885, | |
| "grad_norm": 0.8752704858779907, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 1.0043, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015885623510722795, | |
| "eval_loss": 1.125961422920227, | |
| "eval_runtime": 46.3271, | |
| "eval_samples_per_second": 14.311, | |
| "eval_steps_per_second": 7.166, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01715647339158062, | |
| "grad_norm": 0.8125863671302795, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 1.0368, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.019062748212867357, | |
| "grad_norm": 0.8220617175102234, | |
| "learning_rate": 0.0, | |
| "loss": 1.0301, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019062748212867357, | |
| "eval_loss": 1.1136105060577393, | |
| "eval_runtime": 46.3216, | |
| "eval_samples_per_second": 14.313, | |
| "eval_steps_per_second": 7.167, | |
| "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": 5628994623897600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |