| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0036797775778886254, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001226592525962875, | |
| "eval_loss": 4.26250696182251, | |
| "eval_runtime": 334.4519, | |
| "eval_samples_per_second": 7.699, | |
| "eval_steps_per_second": 3.851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00036797775778886255, | |
| "grad_norm": 1.429119348526001, | |
| "learning_rate": 8.999999999999999e-05, | |
| "loss": 4.1435, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0007359555155777251, | |
| "grad_norm": 2.790388584136963, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 3.7593, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009812740207703, | |
| "eval_loss": 3.0642571449279785, | |
| "eval_runtime": 335.062, | |
| "eval_samples_per_second": 7.685, | |
| "eval_steps_per_second": 3.844, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0011039332733665877, | |
| "grad_norm": 2.1888792514801025, | |
| "learning_rate": 0.00027, | |
| "loss": 3.1196, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014719110311554502, | |
| "grad_norm": 1.176177978515625, | |
| "learning_rate": 0.00029265847744427303, | |
| "loss": 2.4117, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0018398887889443127, | |
| "grad_norm": 2.197014808654785, | |
| "learning_rate": 0.00025606601717798207, | |
| "loss": 2.6601, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0019625480415406, | |
| "eval_loss": 2.3805487155914307, | |
| "eval_runtime": 334.9417, | |
| "eval_samples_per_second": 7.688, | |
| "eval_steps_per_second": 3.845, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0022078665467331754, | |
| "grad_norm": 1.6648246049880981, | |
| "learning_rate": 0.0001963525491562421, | |
| "loss": 2.3264, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0025758443045220377, | |
| "grad_norm": 1.6911269426345825, | |
| "learning_rate": 0.00012653483024396533, | |
| "loss": 2.2865, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0029438220623109004, | |
| "grad_norm": 0.7457146048545837, | |
| "learning_rate": 6.183221215612904e-05, | |
| "loss": 2.0923, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0029438220623109004, | |
| "eval_loss": 2.2382869720458984, | |
| "eval_runtime": 334.9773, | |
| "eval_samples_per_second": 7.687, | |
| "eval_steps_per_second": 3.845, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0033117998200997627, | |
| "grad_norm": 0.9372111558914185, | |
| "learning_rate": 1.634902137174483e-05, | |
| "loss": 2.0104, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0036797775778886254, | |
| "grad_norm": 0.9846737384796143, | |
| "learning_rate": 0.0, | |
| "loss": 1.9179, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.4282526818304e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |