| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0028346679895117285, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00028346679895117287, | |
| "grad_norm": 0.43179750442504883, | |
| "learning_rate": 2e-05, | |
| "loss": 1.688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00028346679895117287, | |
| "eval_loss": 0.5118160843849182, | |
| "eval_runtime": 106.5134, | |
| "eval_samples_per_second": 13.951, | |
| "eval_steps_per_second": 6.976, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005669335979023457, | |
| "grad_norm": 0.6719849705696106, | |
| "learning_rate": 4e-05, | |
| "loss": 2.1461, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008504003968535185, | |
| "grad_norm": 0.7302888631820679, | |
| "learning_rate": 6e-05, | |
| "loss": 2.3268, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008504003968535185, | |
| "eval_loss": 0.5112088322639465, | |
| "eval_runtime": 107.72, | |
| "eval_samples_per_second": 13.795, | |
| "eval_steps_per_second": 6.898, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011338671958046915, | |
| "grad_norm": 0.6751747727394104, | |
| "learning_rate": 8e-05, | |
| "loss": 2.2244, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014173339947558643, | |
| "grad_norm": 0.6359903216362, | |
| "learning_rate": 0.0001, | |
| "loss": 1.922, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001700800793707037, | |
| "grad_norm": 1.8159571886062622, | |
| "learning_rate": 0.00012, | |
| "loss": 2.3929, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001700800793707037, | |
| "eval_loss": 0.5036287307739258, | |
| "eval_runtime": 107.8228, | |
| "eval_samples_per_second": 13.782, | |
| "eval_steps_per_second": 6.891, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00198426759265821, | |
| "grad_norm": 0.5403615236282349, | |
| "learning_rate": 0.00014, | |
| "loss": 1.7168, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002267734391609383, | |
| "grad_norm": 0.9577136635780334, | |
| "learning_rate": 0.00016, | |
| "loss": 1.9064, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025512011905605555, | |
| "grad_norm": 0.9186853766441345, | |
| "learning_rate": 0.00018, | |
| "loss": 2.1106, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025512011905605555, | |
| "eval_loss": 0.46276354789733887, | |
| "eval_runtime": 107.8716, | |
| "eval_samples_per_second": 13.776, | |
| "eval_steps_per_second": 6.888, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0028346679895117285, | |
| "grad_norm": 1.0378309488296509, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9629, | |
| "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": 1669467973091328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |