| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0048997590951778205, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016332530317259402, | |
| "eval_loss": 1.5729252099990845, | |
| "eval_runtime": 152.2568, | |
| "eval_samples_per_second": 16.932, | |
| "eval_steps_per_second": 8.466, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004899759095177821, | |
| "grad_norm": 0.5228143334388733, | |
| "learning_rate": 6e-05, | |
| "loss": 1.4395, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009799518190355642, | |
| "grad_norm": 0.6501123309135437, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2983, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013066024253807521, | |
| "eval_loss": 1.465450644493103, | |
| "eval_runtime": 151.5453, | |
| "eval_samples_per_second": 17.011, | |
| "eval_steps_per_second": 8.506, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014699277285533461, | |
| "grad_norm": 1.7093236446380615, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5798, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019599036380711283, | |
| "grad_norm": 1.011731505393982, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.2087, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0024498795475889103, | |
| "grad_norm": 0.8329542279243469, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.2447, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0026132048507615043, | |
| "eval_loss": 1.359079122543335, | |
| "eval_runtime": 151.828, | |
| "eval_samples_per_second": 16.98, | |
| "eval_steps_per_second": 8.49, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0029398554571066922, | |
| "grad_norm": 0.6340237259864807, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.3165, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.003429831366624474, | |
| "grad_norm": 0.9563743472099304, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.3355, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.003919807276142257, | |
| "grad_norm": 0.9076368808746338, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.3107, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.003919807276142257, | |
| "eval_loss": 1.3322792053222656, | |
| "eval_runtime": 151.5342, | |
| "eval_samples_per_second": 17.013, | |
| "eval_steps_per_second": 8.506, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.004409783185660038, | |
| "grad_norm": 0.8078122735023499, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.2538, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0048997590951778205, | |
| "grad_norm": 0.8908748626708984, | |
| "learning_rate": 0.0, | |
| "loss": 1.2256, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.1406516984741888e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |