| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03686635944700461, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003686635944700461, | |
| "grad_norm": 1.0939016342163086, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2245, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003686635944700461, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.4389, | |
| "eval_samples_per_second": 21.144, | |
| "eval_steps_per_second": 10.664, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007373271889400922, | |
| "grad_norm": 1.028696060180664, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3493, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.011059907834101382, | |
| "grad_norm": 1.0116673707962036, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3174, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011059907834101382, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.6346, | |
| "eval_samples_per_second": 24.813, | |
| "eval_steps_per_second": 12.515, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.014746543778801843, | |
| "grad_norm": 0.9794182777404785, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2789, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.018433179723502304, | |
| "grad_norm": 0.9085415601730347, | |
| "learning_rate": 0.0001, | |
| "loss": 1.3067, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.022119815668202765, | |
| "grad_norm": 0.8947320580482483, | |
| "learning_rate": 0.00012, | |
| "loss": 1.199, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022119815668202765, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.6685, | |
| "eval_samples_per_second": 24.633, | |
| "eval_steps_per_second": 12.424, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.025806451612903226, | |
| "grad_norm": 0.7676160335540771, | |
| "learning_rate": 0.00014, | |
| "loss": 1.1672, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.029493087557603687, | |
| "grad_norm": 0.6877889633178711, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0369, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03317972350230415, | |
| "grad_norm": 0.7596482634544373, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0101, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03317972350230415, | |
| "eval_loss": NaN, | |
| "eval_runtime": 4.6217, | |
| "eval_samples_per_second": 24.883, | |
| "eval_steps_per_second": 12.55, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03686635944700461, | |
| "grad_norm": 0.9022582173347473, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9321, | |
| "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": 511583956500480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |