| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.017616489033735576, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00035232978067471153, | |
| "eval_loss": 13.593902587890625, | |
| "eval_runtime": 302.0833, | |
| "eval_samples_per_second": 3.956, | |
| "eval_steps_per_second": 1.98, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017616489033735576, | |
| "grad_norm": 25.966815948486328, | |
| "learning_rate": 5e-05, | |
| "loss": 13.434, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003523297806747115, | |
| "grad_norm": 34.9310188293457, | |
| "learning_rate": 0.0001, | |
| "loss": 11.1127, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003523297806747115, | |
| "eval_loss": 8.07764720916748, | |
| "eval_runtime": 352.0198, | |
| "eval_samples_per_second": 3.395, | |
| "eval_steps_per_second": 1.699, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005284946710120673, | |
| "grad_norm": 39.66749954223633, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.3819, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00704659561349423, | |
| "grad_norm": 4.8887529373168945, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7644, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00704659561349423, | |
| "eval_loss": 0.3575800955295563, | |
| "eval_runtime": 357.0091, | |
| "eval_samples_per_second": 3.347, | |
| "eval_steps_per_second": 1.675, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008808244516867788, | |
| "grad_norm": 20.166486740112305, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3496, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010569893420241346, | |
| "grad_norm": 8.205277442932129, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1392, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010569893420241346, | |
| "eval_loss": 0.20344699919223785, | |
| "eval_runtime": 357.0046, | |
| "eval_samples_per_second": 3.347, | |
| "eval_steps_per_second": 1.675, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012331542323614903, | |
| "grad_norm": 17.674755096435547, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.2083, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01409319122698846, | |
| "grad_norm": 17.68518829345703, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0759, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01409319122698846, | |
| "eval_loss": 0.1258983165025711, | |
| "eval_runtime": 359.288, | |
| "eval_samples_per_second": 3.326, | |
| "eval_steps_per_second": 1.664, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01585484013036202, | |
| "grad_norm": 1.8895014524459839, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1442, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.017616489033735576, | |
| "grad_norm": 0.18879897892475128, | |
| "learning_rate": 0.0, | |
| "loss": 0.1418, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.017616489033735576, | |
| "eval_loss": 0.13739807903766632, | |
| "eval_runtime": 420.9639, | |
| "eval_samples_per_second": 2.839, | |
| "eval_steps_per_second": 1.421, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.031989364785152e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |