| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016332530317259401, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016332530317259402, | |
| "grad_norm": 1.9298620223999023, | |
| "learning_rate": 2e-05, | |
| "loss": 5.5226, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016332530317259402, | |
| "eval_loss": 1.2396178245544434, | |
| "eval_runtime": 32.8028, | |
| "eval_samples_per_second": 78.591, | |
| "eval_steps_per_second": 39.295, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032665060634518803, | |
| "grad_norm": 2.632509231567383, | |
| "learning_rate": 4e-05, | |
| "loss": 5.8417, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004899759095177821, | |
| "grad_norm": 1.8391531705856323, | |
| "learning_rate": 6e-05, | |
| "loss": 4.8234, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004899759095177821, | |
| "eval_loss": 1.238764762878418, | |
| "eval_runtime": 31.9845, | |
| "eval_samples_per_second": 80.602, | |
| "eval_steps_per_second": 40.301, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006533012126903761, | |
| "grad_norm": 2.708847761154175, | |
| "learning_rate": 8e-05, | |
| "loss": 6.02, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008166265158629701, | |
| "grad_norm": 2.039414644241333, | |
| "learning_rate": 0.0001, | |
| "loss": 5.1642, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009799518190355642, | |
| "grad_norm": 2.06784987449646, | |
| "learning_rate": 0.00012, | |
| "loss": 5.1002, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009799518190355642, | |
| "eval_loss": 1.2361284494400024, | |
| "eval_runtime": 31.8873, | |
| "eval_samples_per_second": 80.847, | |
| "eval_steps_per_second": 40.424, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011432771222081581, | |
| "grad_norm": 2.7405037879943848, | |
| "learning_rate": 0.00014, | |
| "loss": 5.6114, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013066024253807521, | |
| "grad_norm": 2.1372079849243164, | |
| "learning_rate": 0.00016, | |
| "loss": 5.2708, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014699277285533461, | |
| "grad_norm": 1.879054069519043, | |
| "learning_rate": 0.00018, | |
| "loss": 5.0464, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014699277285533461, | |
| "eval_loss": 1.2333914041519165, | |
| "eval_runtime": 31.673, | |
| "eval_samples_per_second": 81.394, | |
| "eval_steps_per_second": 40.697, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016332530317259401, | |
| "grad_norm": 2.1005377769470215, | |
| "learning_rate": 0.0002, | |
| "loss": 4.8574, | |
| "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": 132000786677760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |