| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01278118609406953, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002556237218813906, | |
| "eval_loss": 1.457336664199829, | |
| "eval_runtime": 112.2515, | |
| "eval_samples_per_second": 14.681, | |
| "eval_steps_per_second": 7.341, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001278118609406953, | |
| "grad_norm": 16.06281089782715, | |
| "learning_rate": 5e-05, | |
| "loss": 5.839, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002556237218813906, | |
| "grad_norm": 11.751543998718262, | |
| "learning_rate": 0.0001, | |
| "loss": 5.349, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002556237218813906, | |
| "eval_loss": 1.2705821990966797, | |
| "eval_runtime": 108.9199, | |
| "eval_samples_per_second": 15.13, | |
| "eval_steps_per_second": 7.565, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003834355828220859, | |
| "grad_norm": 7.783527851104736, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.1064, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005112474437627812, | |
| "grad_norm": 9.320758819580078, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.6115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005112474437627812, | |
| "eval_loss": 1.1212003231048584, | |
| "eval_runtime": 106.9353, | |
| "eval_samples_per_second": 15.411, | |
| "eval_steps_per_second": 7.706, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006390593047034765, | |
| "grad_norm": 7.271523952484131, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.2328, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007668711656441718, | |
| "grad_norm": 6.39238977432251, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2716, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007668711656441718, | |
| "eval_loss": 1.0889866352081299, | |
| "eval_runtime": 107.1094, | |
| "eval_samples_per_second": 15.386, | |
| "eval_steps_per_second": 7.693, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00894683026584867, | |
| "grad_norm": 9.798620223999023, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.4171, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010224948875255624, | |
| "grad_norm": 7.218533039093018, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 4.3233, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010224948875255624, | |
| "eval_loss": 1.077911376953125, | |
| "eval_runtime": 107.1075, | |
| "eval_samples_per_second": 15.386, | |
| "eval_steps_per_second": 7.693, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011503067484662576, | |
| "grad_norm": 5.4790568351745605, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 4.5071, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01278118609406953, | |
| "grad_norm": 7.645506381988525, | |
| "learning_rate": 0.0, | |
| "loss": 4.3979, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01278118609406953, | |
| "eval_loss": 1.0752296447753906, | |
| "eval_runtime": 106.9215, | |
| "eval_samples_per_second": 15.413, | |
| "eval_steps_per_second": 7.707, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8763509991014400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |