| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009285051067780872, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009285051067780873, | |
| "grad_norm": 0.4189523458480835, | |
| "learning_rate": 2e-05, | |
| "loss": 1.4026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009285051067780873, | |
| "eval_loss": 1.4490036964416504, | |
| "eval_runtime": 51.0499, | |
| "eval_samples_per_second": 17.767, | |
| "eval_steps_per_second": 4.447, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018570102135561746, | |
| "grad_norm": 0.4775694012641907, | |
| "learning_rate": 4e-05, | |
| "loss": 1.518, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002785515320334262, | |
| "grad_norm": 0.4616241157054901, | |
| "learning_rate": 6e-05, | |
| "loss": 1.5323, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002785515320334262, | |
| "eval_loss": 1.416020154953003, | |
| "eval_runtime": 50.4862, | |
| "eval_samples_per_second": 17.965, | |
| "eval_steps_per_second": 4.496, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003714020427112349, | |
| "grad_norm": 0.41493797302246094, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1808, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004642525533890436, | |
| "grad_norm": 0.44579318165779114, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5362, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005571030640668524, | |
| "grad_norm": 0.4812590777873993, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3197, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005571030640668524, | |
| "eval_loss": 1.2488963603973389, | |
| "eval_runtime": 50.4777, | |
| "eval_samples_per_second": 17.968, | |
| "eval_steps_per_second": 4.497, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0064995357474466105, | |
| "grad_norm": 0.4686659872531891, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2529, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007428040854224698, | |
| "grad_norm": 0.5634918212890625, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2674, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008356545961002786, | |
| "grad_norm": 0.4549058973789215, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0192, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008356545961002786, | |
| "eval_loss": 1.0893065929412842, | |
| "eval_runtime": 50.4729, | |
| "eval_samples_per_second": 17.97, | |
| "eval_steps_per_second": 4.497, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009285051067780872, | |
| "grad_norm": 0.3827737271785736, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0304, | |
| "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": 2.796154706198528e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |