| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0014825796886582653, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014825796886582654, | |
| "grad_norm": 0.7877658605575562, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4327, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014825796886582654, | |
| "eval_loss": 1.423957109451294, | |
| "eval_runtime": 53.3401, | |
| "eval_samples_per_second": 53.243, | |
| "eval_steps_per_second": 26.622, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002965159377316531, | |
| "grad_norm": 0.63080233335495, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3985, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00044477390659747963, | |
| "grad_norm": 0.7581550478935242, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4602, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00044477390659747963, | |
| "eval_loss": 1.4189095497131348, | |
| "eval_runtime": 53.5812, | |
| "eval_samples_per_second": 53.004, | |
| "eval_steps_per_second": 26.502, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0005930318754633062, | |
| "grad_norm": 0.6960687637329102, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3669, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007412898443291327, | |
| "grad_norm": 0.699456512928009, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5292, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0008895478131949593, | |
| "grad_norm": 0.778120756149292, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3721, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0008895478131949593, | |
| "eval_loss": 1.3613526821136475, | |
| "eval_runtime": 53.5086, | |
| "eval_samples_per_second": 53.076, | |
| "eval_steps_per_second": 26.538, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010378057820607859, | |
| "grad_norm": 0.6381222009658813, | |
| "learning_rate": 0.00014, | |
| "loss": 1.3513, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0011860637509266123, | |
| "grad_norm": 0.6122051477432251, | |
| "learning_rate": 0.00016, | |
| "loss": 1.4294, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013343217197924388, | |
| "grad_norm": 0.6916836500167847, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013343217197924388, | |
| "eval_loss": 1.305905818939209, | |
| "eval_runtime": 54.3713, | |
| "eval_samples_per_second": 52.233, | |
| "eval_steps_per_second": 26.117, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014825796886582653, | |
| "grad_norm": 0.8482385277748108, | |
| "learning_rate": 0.0002, | |
| "loss": 1.421, | |
| "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": 155816786657280.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |