| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.044033465433729636, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008806693086745927, | |
| "eval_loss": 2.842715263366699, | |
| "eval_runtime": 28.0509, | |
| "eval_samples_per_second": 17.076, | |
| "eval_steps_per_second": 8.556, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004403346543372964, | |
| "grad_norm": 3.535202741622925, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7568, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008806693086745927, | |
| "grad_norm": 2.774446487426758, | |
| "learning_rate": 0.0001, | |
| "loss": 2.427, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008806693086745927, | |
| "eval_loss": 1.8638564348220825, | |
| "eval_runtime": 28.2356, | |
| "eval_samples_per_second": 16.964, | |
| "eval_steps_per_second": 8.5, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.013210039630118891, | |
| "grad_norm": 1.6853898763656616, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4971, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.017613386173491855, | |
| "grad_norm": 1.6479811668395996, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.376, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017613386173491855, | |
| "eval_loss": 1.3032798767089844, | |
| "eval_runtime": 28.538, | |
| "eval_samples_per_second": 16.785, | |
| "eval_steps_per_second": 8.41, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.022016732716864818, | |
| "grad_norm": 2.3841373920440674, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3518, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.026420079260237782, | |
| "grad_norm": 1.4962481260299683, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3645, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.026420079260237782, | |
| "eval_loss": 1.2372276782989502, | |
| "eval_runtime": 28.8132, | |
| "eval_samples_per_second": 16.624, | |
| "eval_steps_per_second": 8.33, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.030823425803610745, | |
| "grad_norm": 1.2101389169692993, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2336, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03522677234698371, | |
| "grad_norm": 1.8625359535217285, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2459, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03522677234698371, | |
| "eval_loss": 1.205720067024231, | |
| "eval_runtime": 28.8541, | |
| "eval_samples_per_second": 16.601, | |
| "eval_steps_per_second": 8.318, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03963011889035667, | |
| "grad_norm": 1.2852716445922852, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2529, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.044033465433729636, | |
| "grad_norm": 1.3766034841537476, | |
| "learning_rate": 0.0, | |
| "loss": 1.2934, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.044033465433729636, | |
| "eval_loss": 1.2010602951049805, | |
| "eval_runtime": 28.412, | |
| "eval_samples_per_second": 16.859, | |
| "eval_steps_per_second": 8.447, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8239114616832000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |