| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08790242830458192, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004395121415229096, | |
| "eval_loss": 4.948474407196045, | |
| "eval_runtime": 52.4919, | |
| "eval_samples_per_second": 18.269, | |
| "eval_steps_per_second": 9.144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004395121415229096, | |
| "grad_norm": 11.48950481414795, | |
| "learning_rate": 0.0002, | |
| "loss": 14.3578, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008790242830458192, | |
| "grad_norm": 12.444845199584961, | |
| "learning_rate": 0.0002, | |
| "loss": 4.3853, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013185364245687286, | |
| "grad_norm": 9.680885314941406, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6288, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.017580485660916384, | |
| "grad_norm": 4.9109015464782715, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0173, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02197560707614548, | |
| "grad_norm": 15.963685989379883, | |
| "learning_rate": 0.0002, | |
| "loss": 0.5108, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02197560707614548, | |
| "eval_loss": 0.07556916773319244, | |
| "eval_runtime": 52.5274, | |
| "eval_samples_per_second": 18.257, | |
| "eval_steps_per_second": 9.138, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.026370728491374573, | |
| "grad_norm": 19.075408935546875, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3619, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03076584990660367, | |
| "grad_norm": 19.47846794128418, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4093, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03516097132183277, | |
| "grad_norm": 7.209693908691406, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3493, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.039556092737061864, | |
| "grad_norm": 3.2900302410125732, | |
| "learning_rate": 0.0002, | |
| "loss": 0.595, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04395121415229096, | |
| "grad_norm": 7.369869709014893, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4487, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04395121415229096, | |
| "eval_loss": 0.0811665803194046, | |
| "eval_runtime": 52.465, | |
| "eval_samples_per_second": 18.279, | |
| "eval_steps_per_second": 9.149, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.048346335567520056, | |
| "grad_norm": 3.1896722316741943, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3859, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.052741456982749145, | |
| "grad_norm": 1.2178314924240112, | |
| "learning_rate": 0.0002, | |
| "loss": 0.401, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.05713657839797824, | |
| "grad_norm": 6.184231758117676, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4058, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06153169981320734, | |
| "grad_norm": 6.1389899253845215, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3071, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.06592682122843643, | |
| "grad_norm": 4.514057159423828, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2695, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.06592682122843643, | |
| "eval_loss": 0.051861684769392014, | |
| "eval_runtime": 52.5077, | |
| "eval_samples_per_second": 18.264, | |
| "eval_steps_per_second": 9.142, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07032194264366554, | |
| "grad_norm": 4.898068904876709, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2806, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.07471706405889462, | |
| "grad_norm": 4.877391338348389, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3743, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.07911218547412373, | |
| "grad_norm": 5.850367546081543, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1653, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.08350730688935282, | |
| "grad_norm": 5.329926013946533, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3935, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.08790242830458192, | |
| "grad_norm": 10.51096248626709, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2814, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.08790242830458192, | |
| "eval_loss": 0.14480413496494293, | |
| "eval_runtime": 52.5156, | |
| "eval_samples_per_second": 18.261, | |
| "eval_steps_per_second": 9.14, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.216069447634125e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |