| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03971405877680699, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015885623510722795, | |
| "grad_norm": 0.835549533367157, | |
| "learning_rate": 5e-05, | |
| "loss": 1.572, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015885623510722795, | |
| "eval_loss": 1.7700855731964111, | |
| "eval_runtime": 3.4503, | |
| "eval_samples_per_second": 14.491, | |
| "eval_steps_per_second": 3.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003177124702144559, | |
| "grad_norm": 0.895484983921051, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5278, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004765687053216839, | |
| "grad_norm": 0.9265555739402771, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 1.5661, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006354249404289118, | |
| "grad_norm": 0.8144180178642273, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.5381, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007942811755361398, | |
| "grad_norm": 0.865155041217804, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.3875, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009531374106433678, | |
| "grad_norm": 0.6595736145973206, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.3329, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011119936457505957, | |
| "grad_norm": 0.6818419694900513, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.3592, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012708498808578236, | |
| "grad_norm": 0.6055091619491577, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.3013, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014297061159650517, | |
| "grad_norm": 0.6482890248298645, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.26, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015885623510722795, | |
| "grad_norm": 0.6866934299468994, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.3303, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017474185861795076, | |
| "grad_norm": 0.7159948348999023, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.3359, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019062748212867357, | |
| "grad_norm": 0.9179885983467102, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.218, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.020651310563939634, | |
| "grad_norm": 0.8188260197639465, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.1806, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.022239872915011914, | |
| "grad_norm": 0.7819609642028809, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2449, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.023828435266084195, | |
| "grad_norm": 0.4682140648365021, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.1948, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.025416997617156472, | |
| "grad_norm": 0.5395371317863464, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.1915, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.027005559968228753, | |
| "grad_norm": 0.5874021649360657, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1984, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028594122319301033, | |
| "grad_norm": 0.5808006525039673, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2334, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.030182684670373314, | |
| "grad_norm": 0.466338574886322, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.2759, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03177124702144559, | |
| "grad_norm": 0.4269738793373108, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.1977, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03335980937251787, | |
| "grad_norm": 0.41645628213882446, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.1957, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03494837172359015, | |
| "grad_norm": 0.43972092866897583, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.2079, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03653693407466243, | |
| "grad_norm": 0.5166809558868408, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.1493, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03812549642573471, | |
| "grad_norm": 0.5617337226867676, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.0477, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03971405877680699, | |
| "grad_norm": 0.6784234046936035, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.1464, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03971405877680699, | |
| "eval_loss": 1.1754013299942017, | |
| "eval_runtime": 3.5066, | |
| "eval_samples_per_second": 14.259, | |
| "eval_steps_per_second": 3.707, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.984974321220321e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |