| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009285051067780872, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009285051067780873, | |
| "grad_norm": 5.02961540222168, | |
| "learning_rate": 2e-05, | |
| "loss": 43.6855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009285051067780873, | |
| "eval_loss": 10.924467086791992, | |
| "eval_runtime": 1.8695, | |
| "eval_samples_per_second": 242.848, | |
| "eval_steps_per_second": 121.424, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018570102135561746, | |
| "grad_norm": 4.658646106719971, | |
| "learning_rate": 4e-05, | |
| "loss": 43.8249, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002785515320334262, | |
| "grad_norm": 4.925448894500732, | |
| "learning_rate": 6e-05, | |
| "loss": 43.7175, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002785515320334262, | |
| "eval_loss": 10.92429256439209, | |
| "eval_runtime": 0.9984, | |
| "eval_samples_per_second": 454.716, | |
| "eval_steps_per_second": 227.358, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003714020427112349, | |
| "grad_norm": 4.665872097015381, | |
| "learning_rate": 8e-05, | |
| "loss": 43.7149, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004642525533890436, | |
| "grad_norm": 3.9922900199890137, | |
| "learning_rate": 0.0001, | |
| "loss": 43.8772, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005571030640668524, | |
| "grad_norm": 4.797103404998779, | |
| "learning_rate": 0.00012, | |
| "loss": 43.7176, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005571030640668524, | |
| "eval_loss": 10.922677040100098, | |
| "eval_runtime": 1.0356, | |
| "eval_samples_per_second": 438.375, | |
| "eval_steps_per_second": 219.188, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0064995357474466105, | |
| "grad_norm": 4.2232584953308105, | |
| "learning_rate": 0.00014, | |
| "loss": 43.8475, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007428040854224698, | |
| "grad_norm": 4.401081562042236, | |
| "learning_rate": 0.00016, | |
| "loss": 43.7763, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008356545961002786, | |
| "grad_norm": 4.323698043823242, | |
| "learning_rate": 0.00018, | |
| "loss": 43.6932, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008356545961002786, | |
| "eval_loss": 10.883896827697754, | |
| "eval_runtime": 1.0065, | |
| "eval_samples_per_second": 451.084, | |
| "eval_steps_per_second": 225.542, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009285051067780872, | |
| "grad_norm": 3.5456247329711914, | |
| "learning_rate": 0.0002, | |
| "loss": 43.894, | |
| "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": 7844659200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |