| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.006359974560101759, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00021199915200339198, | |
| "eval_loss": 1.9255462884902954, | |
| "eval_runtime": 234.6564, | |
| "eval_samples_per_second": 8.468, | |
| "eval_steps_per_second": 4.236, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006359974560101759, | |
| "grad_norm": 0.5463253259658813, | |
| "learning_rate": 6e-05, | |
| "loss": 8.0554, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012719949120203519, | |
| "grad_norm": 0.429708868265152, | |
| "learning_rate": 0.00012, | |
| "loss": 7.4225, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016959932160271359, | |
| "eval_loss": 1.8925036191940308, | |
| "eval_runtime": 236.0614, | |
| "eval_samples_per_second": 8.417, | |
| "eval_steps_per_second": 4.211, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0019079923680305278, | |
| "grad_norm": 0.5673459768295288, | |
| "learning_rate": 0.00018, | |
| "loss": 7.3739, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0025439898240407037, | |
| "grad_norm": 0.8614652156829834, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 7.1525, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0031799872800508796, | |
| "grad_norm": 0.9778960943222046, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 7.2018, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0033919864320542717, | |
| "eval_loss": 1.7460987567901611, | |
| "eval_runtime": 236.067, | |
| "eval_samples_per_second": 8.417, | |
| "eval_steps_per_second": 4.211, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0038159847360610556, | |
| "grad_norm": 1.2029049396514893, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 7.1342, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0044519821920712315, | |
| "grad_norm": 1.1358927488327026, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 6.8089, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005087979648081407, | |
| "grad_norm": 1.0122755765914917, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 6.5714, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005087979648081407, | |
| "eval_loss": 1.7018647193908691, | |
| "eval_runtime": 235.9213, | |
| "eval_samples_per_second": 8.422, | |
| "eval_steps_per_second": 4.213, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005723977104091583, | |
| "grad_norm": 1.0656787157058716, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 6.6396, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006359974560101759, | |
| "grad_norm": 1.0406821966171265, | |
| "learning_rate": 0.0, | |
| "loss": 6.6495, | |
| "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": 3109852758933504.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |