| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016332530317259401, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016332530317259402, | |
| "grad_norm": 0.006969714071601629, | |
| "learning_rate": 2e-05, | |
| "loss": 11.9318, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016332530317259402, | |
| "eval_loss": 11.932430267333984, | |
| "eval_runtime": 8.5724, | |
| "eval_samples_per_second": 300.733, | |
| "eval_steps_per_second": 150.367, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032665060634518803, | |
| "grad_norm": 0.012661618180572987, | |
| "learning_rate": 4e-05, | |
| "loss": 11.933, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004899759095177821, | |
| "grad_norm": 0.017709046602249146, | |
| "learning_rate": 6e-05, | |
| "loss": 11.923, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004899759095177821, | |
| "eval_loss": 11.932427406311035, | |
| "eval_runtime": 8.6334, | |
| "eval_samples_per_second": 298.606, | |
| "eval_steps_per_second": 149.303, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006533012126903761, | |
| "grad_norm": 0.0069983652792871, | |
| "learning_rate": 8e-05, | |
| "loss": 11.9312, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008166265158629701, | |
| "grad_norm": 0.01158211100846529, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9341, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009799518190355642, | |
| "grad_norm": 0.0077381432056427, | |
| "learning_rate": 0.00012, | |
| "loss": 11.9312, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009799518190355642, | |
| "eval_loss": 11.932414054870605, | |
| "eval_runtime": 8.7213, | |
| "eval_samples_per_second": 295.597, | |
| "eval_steps_per_second": 147.799, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011432771222081581, | |
| "grad_norm": 0.010349428281188011, | |
| "learning_rate": 0.00014, | |
| "loss": 11.9306, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013066024253807521, | |
| "grad_norm": 0.006527108605951071, | |
| "learning_rate": 0.00016, | |
| "loss": 11.9317, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014699277285533461, | |
| "grad_norm": 0.01932574063539505, | |
| "learning_rate": 0.00018, | |
| "loss": 11.9334, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014699277285533461, | |
| "eval_loss": 11.932388305664062, | |
| "eval_runtime": 8.6392, | |
| "eval_samples_per_second": 298.406, | |
| "eval_steps_per_second": 149.203, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016332530317259401, | |
| "grad_norm": 0.013241647742688656, | |
| "learning_rate": 0.0002, | |
| "loss": 11.9294, | |
| "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": 1270235136.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |