| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013343118286743613, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002668623657348722, | |
| "eval_loss": 1.4171478748321533, | |
| "eval_runtime": 51.4601, | |
| "eval_samples_per_second": 30.665, | |
| "eval_steps_per_second": 15.332, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0013343118286743613, | |
| "grad_norm": 0.20870009064674377, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1958, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0026686236573487225, | |
| "grad_norm": 0.3936935365200043, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4671, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0026686236573487225, | |
| "eval_loss": 1.3937021493911743, | |
| "eval_runtime": 51.4019, | |
| "eval_samples_per_second": 30.699, | |
| "eval_steps_per_second": 15.35, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004002935486023084, | |
| "grad_norm": 0.2306661754846573, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3999, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005337247314697445, | |
| "grad_norm": 0.28997236490249634, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3391, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005337247314697445, | |
| "eval_loss": 1.331410527229309, | |
| "eval_runtime": 51.2329, | |
| "eval_samples_per_second": 30.801, | |
| "eval_steps_per_second": 15.4, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006671559143371806, | |
| "grad_norm": 0.2963295876979828, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3088, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.008005870972046168, | |
| "grad_norm": 0.3198167383670807, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3884, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008005870972046168, | |
| "eval_loss": 1.3172019720077515, | |
| "eval_runtime": 51.3541, | |
| "eval_samples_per_second": 30.728, | |
| "eval_steps_per_second": 15.364, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009340182800720529, | |
| "grad_norm": 0.271278440952301, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2783, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01067449462939489, | |
| "grad_norm": 0.31695592403411865, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.2705, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01067449462939489, | |
| "eval_loss": 1.3098112344741821, | |
| "eval_runtime": 52.1649, | |
| "eval_samples_per_second": 30.25, | |
| "eval_steps_per_second": 15.125, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012008806458069251, | |
| "grad_norm": 0.33602485060691833, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2586, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013343118286743613, | |
| "grad_norm": 0.3920798599720001, | |
| "learning_rate": 0.0, | |
| "loss": 1.3313, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013343118286743613, | |
| "eval_loss": 1.3084073066711426, | |
| "eval_runtime": 52.5608, | |
| "eval_samples_per_second": 30.022, | |
| "eval_steps_per_second": 15.011, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1752175051014144.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |