| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 2.1120104789733887, | |
| "learning_rate": 4.9214579028215776e-05, | |
| "loss": 0.6061, | |
| "num_input_tokens_seen": 32448, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 3.365793228149414, | |
| "learning_rate": 4.690766700109659e-05, | |
| "loss": 0.354, | |
| "num_input_tokens_seen": 64640, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 4.048572540283203, | |
| "learning_rate": 4.3224215685535294e-05, | |
| "loss": 0.3654, | |
| "num_input_tokens_seen": 97312, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 11.761089324951172, | |
| "learning_rate": 3.8395669874474915e-05, | |
| "loss": 0.316, | |
| "num_input_tokens_seen": 128960, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 8.3576078414917, | |
| "learning_rate": 3.272542485937369e-05, | |
| "loss": 0.3752, | |
| "num_input_tokens_seen": 161904, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 3.2308974266052246, | |
| "learning_rate": 2.656976298823284e-05, | |
| "loss": 0.2698, | |
| "num_input_tokens_seen": 193568, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 3.596054792404175, | |
| "learning_rate": 2.031546713535688e-05, | |
| "loss": 0.2602, | |
| "num_input_tokens_seen": 225264, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 4.938518524169922, | |
| "learning_rate": 1.4355517710873184e-05, | |
| "loss": 0.2667, | |
| "num_input_tokens_seen": 257376, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 9.911075592041016, | |
| "learning_rate": 9.064400256282757e-06, | |
| "loss": 0.2667, | |
| "num_input_tokens_seen": 289728, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 4.612339973449707, | |
| "learning_rate": 4.7745751406263165e-06, | |
| "loss": 0.2298, | |
| "num_input_tokens_seen": 322000, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 4.9222307205200195, | |
| "learning_rate": 1.7555878527937164e-06, | |
| "loss": 0.2468, | |
| "num_input_tokens_seen": 354432, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 6.1633620262146, | |
| "learning_rate": 1.9713246713805588e-07, | |
| "loss": 0.2118, | |
| "num_input_tokens_seen": 386896, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "num_input_tokens_seen": 403072, | |
| "step": 125, | |
| "total_flos": 1.7254973841604608e+16, | |
| "train_loss": 0.3098531789779663, | |
| "train_runtime": 8159.7352, | |
| "train_samples_per_second": 0.123, | |
| "train_steps_per_second": 0.015 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 403072, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7254973841604608e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |