| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0847457627118644, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002824858757062147, | |
| "eval_loss": 1.9134138822555542, | |
| "eval_runtime": 17.0767, | |
| "eval_samples_per_second": 8.784, | |
| "eval_steps_per_second": 4.392, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00847457627118644, | |
| "grad_norm": 22.408552169799805, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9676, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014124293785310734, | |
| "eval_loss": 1.819502592086792, | |
| "eval_runtime": 17.0594, | |
| "eval_samples_per_second": 8.793, | |
| "eval_steps_per_second": 4.396, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01694915254237288, | |
| "grad_norm": 20.456899642944336, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8743, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025423728813559324, | |
| "grad_norm": 2.078036069869995, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7442, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02824858757062147, | |
| "eval_loss": 1.6691161394119263, | |
| "eval_runtime": 17.0825, | |
| "eval_samples_per_second": 8.781, | |
| "eval_steps_per_second": 4.39, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03389830508474576, | |
| "grad_norm": 0.814409077167511, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.5952, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0423728813559322, | |
| "grad_norm": 0.873404324054718, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.5137, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0423728813559322, | |
| "eval_loss": 1.5807734727859497, | |
| "eval_runtime": 17.144, | |
| "eval_samples_per_second": 8.749, | |
| "eval_steps_per_second": 4.375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05084745762711865, | |
| "grad_norm": 0.7489776611328125, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.5281, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05649717514124294, | |
| "eval_loss": 1.543881893157959, | |
| "eval_runtime": 17.093, | |
| "eval_samples_per_second": 8.776, | |
| "eval_steps_per_second": 4.388, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.059322033898305086, | |
| "grad_norm": 0.7277962565422058, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.566, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06779661016949153, | |
| "grad_norm": 0.6766118407249451, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.4651, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07062146892655367, | |
| "eval_loss": 1.5247591733932495, | |
| "eval_runtime": 17.0437, | |
| "eval_samples_per_second": 8.801, | |
| "eval_steps_per_second": 4.4, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07627118644067797, | |
| "grad_norm": 0.7272737622261047, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.534, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "grad_norm": 0.6504532694816589, | |
| "learning_rate": 0.0, | |
| "loss": 1.4885, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "eval_loss": 1.5210504531860352, | |
| "eval_runtime": 17.1088, | |
| "eval_samples_per_second": 8.767, | |
| "eval_steps_per_second": 4.384, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3015894871572480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |