| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.001038772171293531, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010387721712935311, | |
| "grad_norm": 1.5019885301589966, | |
| "learning_rate": 2e-05, | |
| "loss": 1.939, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010387721712935311, | |
| "eval_loss": 1.901095986366272, | |
| "eval_runtime": 112.8269, | |
| "eval_samples_per_second": 35.931, | |
| "eval_steps_per_second": 17.966, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00020775443425870621, | |
| "grad_norm": 1.2988160848617554, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6544, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0003116316513880593, | |
| "grad_norm": 1.1926392316818237, | |
| "learning_rate": 6e-05, | |
| "loss": 1.779, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003116316513880593, | |
| "eval_loss": 1.8887230157852173, | |
| "eval_runtime": 113.1435, | |
| "eval_samples_per_second": 35.831, | |
| "eval_steps_per_second": 17.915, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00041550886851741243, | |
| "grad_norm": 1.465193510055542, | |
| "learning_rate": 8e-05, | |
| "loss": 1.8448, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0005193860856467655, | |
| "grad_norm": 1.385634422302246, | |
| "learning_rate": 0.0001, | |
| "loss": 1.8131, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0006232633027761186, | |
| "grad_norm": 1.5537233352661133, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8471, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006232633027761186, | |
| "eval_loss": 1.7395198345184326, | |
| "eval_runtime": 112.8668, | |
| "eval_samples_per_second": 35.918, | |
| "eval_steps_per_second": 17.959, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0007271405199054717, | |
| "grad_norm": 1.1893061399459839, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5154, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0008310177370348249, | |
| "grad_norm": 1.1050771474838257, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3836, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0009348949541641779, | |
| "grad_norm": 1.5559436082839966, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5296, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009348949541641779, | |
| "eval_loss": 1.5618540048599243, | |
| "eval_runtime": 114.3143, | |
| "eval_samples_per_second": 35.464, | |
| "eval_steps_per_second": 17.732, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.001038772171293531, | |
| "grad_norm": 1.6389344930648804, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7169, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 512599763976192.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |