| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04614142346291383, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018456569385165533, | |
| "grad_norm": 2.75396990776062, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1371, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018456569385165533, | |
| "eval_loss": 2.748347520828247, | |
| "eval_runtime": 4.0137, | |
| "eval_samples_per_second": 12.457, | |
| "eval_steps_per_second": 3.239, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036913138770331066, | |
| "grad_norm": 3.033623456954956, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3339, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0055369708155496595, | |
| "grad_norm": 2.5768418312072754, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.1546, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007382627754066213, | |
| "grad_norm": 1.489610195159912, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.8044, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009228284692582767, | |
| "grad_norm": 2.8157870769500732, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.7984, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011073941631099319, | |
| "grad_norm": 1.6976666450500488, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.6729, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.012919598569615873, | |
| "grad_norm": 1.422610878944397, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.6645, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.014765255508132426, | |
| "grad_norm": 0.9666727185249329, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.6601, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01661091244664898, | |
| "grad_norm": 1.1793878078460693, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.751, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018456569385165534, | |
| "grad_norm": 1.6975785493850708, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.7146, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020302226323682084, | |
| "grad_norm": 1.1711910963058472, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.6701, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.022147883262198638, | |
| "grad_norm": 1.6735578775405884, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.8805, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02399354020071519, | |
| "grad_norm": 1.4089785814285278, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.7491, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.025839197139231745, | |
| "grad_norm": 0.7647345066070557, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.5057, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0276848540777483, | |
| "grad_norm": 0.9470804929733276, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.4528, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.029530511016264853, | |
| "grad_norm": 0.5536386370658875, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.4882, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0313761679547814, | |
| "grad_norm": 0.6176409721374512, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.499, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03322182489329796, | |
| "grad_norm": 0.5578486919403076, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.4011, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03506748183181451, | |
| "grad_norm": 0.5834951400756836, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.4386, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03691313877033107, | |
| "grad_norm": 0.7230275869369507, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.4154, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03875879570884762, | |
| "grad_norm": 0.6893210411071777, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.3899, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04060445264736417, | |
| "grad_norm": 0.7701072096824646, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4799, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.042450109585880726, | |
| "grad_norm": 1.052131175994873, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.5931, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.044295766524397276, | |
| "grad_norm": 1.002185344696045, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.5369, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04614142346291383, | |
| "grad_norm": 1.3195841312408447, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.5881, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04614142346291383, | |
| "eval_loss": 1.5817081928253174, | |
| "eval_runtime": 4.0733, | |
| "eval_samples_per_second": 12.275, | |
| "eval_steps_per_second": 3.192, | |
| "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": 3.140301620206633e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |