| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014937759336099586, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016597510373443983, | |
| "grad_norm": 0.8111277222633362, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5565, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016597510373443983, | |
| "eval_loss": 0.49270984530448914, | |
| "eval_runtime": 14.6125, | |
| "eval_samples_per_second": 17.382, | |
| "eval_steps_per_second": 8.691, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033195020746887966, | |
| "grad_norm": 0.5959430932998657, | |
| "learning_rate": 4e-05, | |
| "loss": 0.4676, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004979253112033195, | |
| "grad_norm": 0.6157602667808533, | |
| "learning_rate": 6e-05, | |
| "loss": 0.5478, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004979253112033195, | |
| "eval_loss": 0.4775579273700714, | |
| "eval_runtime": 12.5706, | |
| "eval_samples_per_second": 20.206, | |
| "eval_steps_per_second": 10.103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006639004149377593, | |
| "grad_norm": 0.4995167851448059, | |
| "learning_rate": 8e-05, | |
| "loss": 0.428, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008298755186721992, | |
| "grad_norm": 0.4362528920173645, | |
| "learning_rate": 0.0001, | |
| "loss": 0.427, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00995850622406639, | |
| "grad_norm": 0.35837677121162415, | |
| "learning_rate": 0.00012, | |
| "loss": 0.3855, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00995850622406639, | |
| "eval_loss": 0.37571078538894653, | |
| "eval_runtime": 12.6561, | |
| "eval_samples_per_second": 20.069, | |
| "eval_steps_per_second": 10.035, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011618257261410789, | |
| "grad_norm": 0.3038789629936218, | |
| "learning_rate": 0.00014, | |
| "loss": 0.343, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013278008298755186, | |
| "grad_norm": 0.29985228180885315, | |
| "learning_rate": 0.00016, | |
| "loss": 0.2773, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014937759336099586, | |
| "grad_norm": 0.38474905490875244, | |
| "learning_rate": 0.00018, | |
| "loss": 0.3235, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014937759336099586, | |
| "eval_loss": 0.2738620340824127, | |
| "eval_runtime": 12.7069, | |
| "eval_samples_per_second": 19.989, | |
| "eval_steps_per_second": 9.995, | |
| "step": 9 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2711820020219904.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |