| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04028197381671702, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004028197381671702, | |
| "grad_norm": 16.487520217895508, | |
| "learning_rate": 2e-05, | |
| "loss": 19.1327, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004028197381671702, | |
| "eval_loss": 3.9355733394622803, | |
| "eval_runtime": 1.468, | |
| "eval_samples_per_second": 71.528, | |
| "eval_steps_per_second": 36.105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008056394763343404, | |
| "grad_norm": 13.663741111755371, | |
| "learning_rate": 4e-05, | |
| "loss": 14.9019, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012084592145015106, | |
| "grad_norm": 15.333662033081055, | |
| "learning_rate": 6e-05, | |
| "loss": 15.7005, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012084592145015106, | |
| "eval_loss": 3.9295601844787598, | |
| "eval_runtime": 1.4877, | |
| "eval_samples_per_second": 70.577, | |
| "eval_steps_per_second": 35.625, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016112789526686808, | |
| "grad_norm": 15.097208023071289, | |
| "learning_rate": 8e-05, | |
| "loss": 15.5187, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02014098690835851, | |
| "grad_norm": 13.481897354125977, | |
| "learning_rate": 0.0001, | |
| "loss": 15.1496, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02416918429003021, | |
| "grad_norm": 15.7518949508667, | |
| "learning_rate": 0.00012, | |
| "loss": 13.9951, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02416918429003021, | |
| "eval_loss": 3.5103189945220947, | |
| "eval_runtime": 1.5424, | |
| "eval_samples_per_second": 68.075, | |
| "eval_steps_per_second": 34.361, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.028197381671701913, | |
| "grad_norm": 16.026578903198242, | |
| "learning_rate": 0.00014, | |
| "loss": 13.141, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.032225579053373615, | |
| "grad_norm": 12.509324073791504, | |
| "learning_rate": 0.00016, | |
| "loss": 12.7861, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03625377643504532, | |
| "grad_norm": 13.980443954467773, | |
| "learning_rate": 0.00018, | |
| "loss": 12.8322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03625377643504532, | |
| "eval_loss": 2.8865890502929688, | |
| "eval_runtime": 1.4984, | |
| "eval_samples_per_second": 70.077, | |
| "eval_steps_per_second": 35.372, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04028197381671702, | |
| "grad_norm": 11.624281883239746, | |
| "learning_rate": 0.0002, | |
| "loss": 11.3334, | |
| "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": 75069652992000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |