| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.7308970099667774, | |
| "eval_steps": 14, | |
| "global_step": 55, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013289036544850499, | |
| "eval_loss": 2.4356181621551514, | |
| "eval_runtime": 0.8063, | |
| "eval_samples_per_second": 39.685, | |
| "eval_steps_per_second": 19.843, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.132890365448505, | |
| "grad_norm": 3.1786859035491943, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.7808, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.18604651162790697, | |
| "eval_loss": 1.3662489652633667, | |
| "eval_runtime": 0.8213, | |
| "eval_samples_per_second": 38.962, | |
| "eval_steps_per_second": 19.481, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.26578073089701, | |
| "grad_norm": 2.2089364528656006, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 1.2664, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.37209302325581395, | |
| "eval_loss": 1.2207937240600586, | |
| "eval_runtime": 0.8151, | |
| "eval_samples_per_second": 39.257, | |
| "eval_steps_per_second": 19.629, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.39867109634551495, | |
| "grad_norm": 1.859800934791565, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1239, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.53156146179402, | |
| "grad_norm": 1.8808262348175049, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.2634, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5581395348837209, | |
| "eval_loss": 1.203535795211792, | |
| "eval_runtime": 0.8233, | |
| "eval_samples_per_second": 38.867, | |
| "eval_steps_per_second": 19.434, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6644518272425249, | |
| "grad_norm": 1.8351376056671143, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 0.9498, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 55, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 14, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2750535318896640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |