| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012244897959183673, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00040816326530612246, | |
| "eval_loss": 1.3330155611038208, | |
| "eval_runtime": 72.1822, | |
| "eval_samples_per_second": 14.297, | |
| "eval_steps_per_second": 7.149, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012244897959183673, | |
| "grad_norm": 2.0126116275787354, | |
| "learning_rate": 6e-05, | |
| "loss": 4.883, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024489795918367346, | |
| "grad_norm": 1.7460933923721313, | |
| "learning_rate": 0.00012, | |
| "loss": 5.1913, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032653061224489797, | |
| "eval_loss": 1.1873412132263184, | |
| "eval_runtime": 71.2572, | |
| "eval_samples_per_second": 14.483, | |
| "eval_steps_per_second": 7.241, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003673469387755102, | |
| "grad_norm": 1.6684772968292236, | |
| "learning_rate": 0.00018, | |
| "loss": 4.5746, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004897959183673469, | |
| "grad_norm": 2.312330961227417, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 4.6686, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006122448979591836, | |
| "grad_norm": 2.092863082885742, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 4.0921, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006530612244897959, | |
| "eval_loss": 1.0457439422607422, | |
| "eval_runtime": 71.3543, | |
| "eval_samples_per_second": 14.463, | |
| "eval_steps_per_second": 7.232, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007346938775510204, | |
| "grad_norm": 1.790899395942688, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 4.1099, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008571428571428572, | |
| "grad_norm": 1.987960696220398, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 4.4062, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009795918367346938, | |
| "grad_norm": 1.5989941358566284, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 3.8699, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009795918367346938, | |
| "eval_loss": 0.9915894269943237, | |
| "eval_runtime": 71.3937, | |
| "eval_samples_per_second": 14.455, | |
| "eval_steps_per_second": 7.228, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011020408163265306, | |
| "grad_norm": 2.049525499343872, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 4.1971, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012244897959183673, | |
| "grad_norm": 2.069650411605835, | |
| "learning_rate": 0.0, | |
| "loss": 3.7882, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.772334209826816e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |