| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.025412960609911054, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025412960609911056, | |
| "grad_norm": 0.2694489061832428, | |
| "learning_rate": 2e-05, | |
| "loss": 5.4593, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025412960609911056, | |
| "eval_loss": 5.5072832107543945, | |
| "eval_runtime": 5.1676, | |
| "eval_samples_per_second": 32.123, | |
| "eval_steps_per_second": 16.062, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005082592121982211, | |
| "grad_norm": 0.37336480617523193, | |
| "learning_rate": 4e-05, | |
| "loss": 5.4793, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007623888182973317, | |
| "grad_norm": 0.29353266954421997, | |
| "learning_rate": 6e-05, | |
| "loss": 5.4156, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007623888182973317, | |
| "eval_loss": 5.5053815841674805, | |
| "eval_runtime": 4.0708, | |
| "eval_samples_per_second": 40.778, | |
| "eval_steps_per_second": 20.389, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010165184243964422, | |
| "grad_norm": 0.4207238256931305, | |
| "learning_rate": 8e-05, | |
| "loss": 5.4398, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012706480304955527, | |
| "grad_norm": 0.40501707792282104, | |
| "learning_rate": 0.0001, | |
| "loss": 5.4969, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015247776365946633, | |
| "grad_norm": 0.26661601662635803, | |
| "learning_rate": 0.00012, | |
| "loss": 5.4325, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015247776365946633, | |
| "eval_loss": 5.472946643829346, | |
| "eval_runtime": 4.1557, | |
| "eval_samples_per_second": 39.945, | |
| "eval_steps_per_second": 19.972, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017789072426937738, | |
| "grad_norm": 0.33637258410453796, | |
| "learning_rate": 0.00014, | |
| "loss": 5.4078, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.020330368487928845, | |
| "grad_norm": 0.4484331011772156, | |
| "learning_rate": 0.00016, | |
| "loss": 5.4027, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022871664548919948, | |
| "grad_norm": 0.40409019589424133, | |
| "learning_rate": 0.00018, | |
| "loss": 5.3888, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.022871664548919948, | |
| "eval_loss": 5.433940410614014, | |
| "eval_runtime": 4.1558, | |
| "eval_samples_per_second": 39.944, | |
| "eval_steps_per_second": 19.972, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025412960609911054, | |
| "grad_norm": 0.45385488867759705, | |
| "learning_rate": 0.0002, | |
| "loss": 5.3359, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 719886967898112.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |