| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008967001434720229, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000896700143472023, | |
| "grad_norm": 1.124503254890442, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3789, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000896700143472023, | |
| "eval_loss": 1.9937291145324707, | |
| "eval_runtime": 65.4243, | |
| "eval_samples_per_second": 2.736, | |
| "eval_steps_per_second": 1.376, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001793400286944046, | |
| "grad_norm": 0.8716641664505005, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7336, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.001793400286944046, | |
| "eval_loss": 1.590023398399353, | |
| "eval_runtime": 63.9353, | |
| "eval_samples_per_second": 2.8, | |
| "eval_steps_per_second": 1.408, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002690100430416069, | |
| "grad_norm": 0.5799658298492432, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6249, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.002690100430416069, | |
| "eval_loss": 1.4548176527023315, | |
| "eval_runtime": 63.7041, | |
| "eval_samples_per_second": 2.81, | |
| "eval_steps_per_second": 1.413, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003586800573888092, | |
| "grad_norm": 0.6462221145629883, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3909, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003586800573888092, | |
| "eval_loss": 1.3800599575042725, | |
| "eval_runtime": 64.2415, | |
| "eval_samples_per_second": 2.786, | |
| "eval_steps_per_second": 1.401, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0044835007173601145, | |
| "grad_norm": 0.5445486903190613, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3388, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0044835007173601145, | |
| "eval_loss": 1.3405883312225342, | |
| "eval_runtime": 63.9014, | |
| "eval_samples_per_second": 2.801, | |
| "eval_steps_per_second": 1.408, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005380200860832138, | |
| "grad_norm": 0.5416566133499146, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2852, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005380200860832138, | |
| "eval_loss": 1.3104169368743896, | |
| "eval_runtime": 64.3636, | |
| "eval_samples_per_second": 2.781, | |
| "eval_steps_per_second": 1.398, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006276901004304161, | |
| "grad_norm": 0.5696709752082825, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2838, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006276901004304161, | |
| "eval_loss": 1.289123773574829, | |
| "eval_runtime": 63.7213, | |
| "eval_samples_per_second": 2.809, | |
| "eval_steps_per_second": 1.412, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007173601147776184, | |
| "grad_norm": 0.5097543597221375, | |
| "learning_rate": 4e-05, | |
| "loss": 1.2537, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007173601147776184, | |
| "eval_loss": 1.2738059759140015, | |
| "eval_runtime": 64.6891, | |
| "eval_samples_per_second": 2.767, | |
| "eval_steps_per_second": 1.391, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008070301291248206, | |
| "grad_norm": 0.5577636957168579, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2054, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008070301291248206, | |
| "eval_loss": 1.2649672031402588, | |
| "eval_runtime": 64.54, | |
| "eval_samples_per_second": 2.773, | |
| "eval_steps_per_second": 1.394, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.008967001434720229, | |
| "grad_norm": 0.483451247215271, | |
| "learning_rate": 0.0, | |
| "loss": 1.2729, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.008967001434720229, | |
| "eval_loss": 1.2614667415618896, | |
| "eval_runtime": 64.4176, | |
| "eval_samples_per_second": 2.779, | |
| "eval_steps_per_second": 1.397, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6694253847865152.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |