| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.27624309392265195, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0055248618784530384, | |
| "eval_loss": 2.3961617946624756, | |
| "eval_runtime": 14.3555, | |
| "eval_samples_per_second": 21.246, | |
| "eval_steps_per_second": 2.717, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016574585635359115, | |
| "grad_norm": 5.99178409576416, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3977, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.027624309392265192, | |
| "eval_loss": 1.7959058284759521, | |
| "eval_runtime": 14.0004, | |
| "eval_samples_per_second": 21.785, | |
| "eval_steps_per_second": 2.786, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03314917127071823, | |
| "grad_norm": 2.2346062660217285, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9546, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.049723756906077346, | |
| "grad_norm": 1.8098475933074951, | |
| "learning_rate": 9e-05, | |
| "loss": 1.4476, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.055248618784530384, | |
| "eval_loss": 0.9513735771179199, | |
| "eval_runtime": 14.0641, | |
| "eval_samples_per_second": 21.686, | |
| "eval_steps_per_second": 2.773, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06629834254143646, | |
| "grad_norm": 0.8746972680091858, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.9539, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08287292817679558, | |
| "grad_norm": 0.6028872728347778, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.8474, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08287292817679558, | |
| "eval_loss": 0.7902776002883911, | |
| "eval_runtime": 14.105, | |
| "eval_samples_per_second": 21.624, | |
| "eval_steps_per_second": 2.765, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09944751381215469, | |
| "grad_norm": 0.626864492893219, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.7667, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11049723756906077, | |
| "eval_loss": 0.7543848752975464, | |
| "eval_runtime": 14.1327, | |
| "eval_samples_per_second": 21.581, | |
| "eval_steps_per_second": 2.76, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11602209944751381, | |
| "grad_norm": 0.5081455111503601, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.8152, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.13259668508287292, | |
| "grad_norm": 0.48921826481819153, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.7473, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.13812154696132597, | |
| "eval_loss": 0.7393178343772888, | |
| "eval_runtime": 14.1193, | |
| "eval_samples_per_second": 21.602, | |
| "eval_steps_per_second": 2.762, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14917127071823205, | |
| "grad_norm": 0.4387621581554413, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.688, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16574585635359115, | |
| "grad_norm": 0.4396769404411316, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7162, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.16574585635359115, | |
| "eval_loss": 0.7258535027503967, | |
| "eval_runtime": 14.1233, | |
| "eval_samples_per_second": 21.596, | |
| "eval_steps_per_second": 2.761, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18232044198895028, | |
| "grad_norm": 0.3995254933834076, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.7043, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19337016574585636, | |
| "eval_loss": 0.7178325057029724, | |
| "eval_runtime": 14.1201, | |
| "eval_samples_per_second": 21.6, | |
| "eval_steps_per_second": 2.762, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19889502762430938, | |
| "grad_norm": 0.4234910011291504, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.7229, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2154696132596685, | |
| "grad_norm": 0.40198755264282227, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.7506, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.22099447513812154, | |
| "eval_loss": 0.7135867476463318, | |
| "eval_runtime": 14.1258, | |
| "eval_samples_per_second": 21.592, | |
| "eval_steps_per_second": 2.761, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23204419889502761, | |
| "grad_norm": 0.3898721933364868, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.718, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.24861878453038674, | |
| "grad_norm": 0.4483630955219269, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7457, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.24861878453038674, | |
| "eval_loss": 0.7124005556106567, | |
| "eval_runtime": 14.1279, | |
| "eval_samples_per_second": 21.588, | |
| "eval_steps_per_second": 2.76, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.26519337016574585, | |
| "grad_norm": 0.38979488611221313, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.6953, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.27624309392265195, | |
| "eval_loss": 0.7120224237442017, | |
| "eval_runtime": 14.122, | |
| "eval_samples_per_second": 21.598, | |
| "eval_steps_per_second": 2.762, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.84541717577728e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |