| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0396000396000396, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000198000198000198, | |
| "eval_loss": 1.1046350002288818, | |
| "eval_runtime": 177.7012, | |
| "eval_samples_per_second": 11.97, | |
| "eval_steps_per_second": 5.988, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00198000198000198, | |
| "grad_norm": 1.1289453506469727, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1006, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00396000396000396, | |
| "grad_norm": 1.3300156593322754, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7418, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00594000594000594, | |
| "grad_norm": 1.6589006185531616, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7895, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00792000792000792, | |
| "grad_norm": 1.0909771919250488, | |
| "learning_rate": 0.0002, | |
| "loss": 3.6444, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0099000099000099, | |
| "grad_norm": 1.8193849325180054, | |
| "learning_rate": 0.0002, | |
| "loss": 3.92, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0099000099000099, | |
| "eval_loss": 0.8933662176132202, | |
| "eval_runtime": 177.8394, | |
| "eval_samples_per_second": 11.96, | |
| "eval_steps_per_second": 5.983, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01188001188001188, | |
| "grad_norm": 1.5985904932022095, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7766, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01386001386001386, | |
| "grad_norm": 1.0298365354537964, | |
| "learning_rate": 0.0002, | |
| "loss": 3.9574, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01584001584001584, | |
| "grad_norm": 1.3167791366577148, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5841, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01782001782001782, | |
| "grad_norm": 1.6314549446105957, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5142, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0198000198000198, | |
| "grad_norm": 0.9245526790618896, | |
| "learning_rate": 0.0002, | |
| "loss": 3.4552, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0198000198000198, | |
| "eval_loss": 0.8583095669746399, | |
| "eval_runtime": 177.6926, | |
| "eval_samples_per_second": 11.97, | |
| "eval_steps_per_second": 5.988, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02178002178002178, | |
| "grad_norm": 0.9592312574386597, | |
| "learning_rate": 0.0002, | |
| "loss": 3.1673, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02376002376002376, | |
| "grad_norm": 1.070432186126709, | |
| "learning_rate": 0.0002, | |
| "loss": 3.1173, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02574002574002574, | |
| "grad_norm": 2.247570753097534, | |
| "learning_rate": 0.0002, | |
| "loss": 3.7768, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02772002772002772, | |
| "grad_norm": 1.5730074644088745, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3516, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0297000297000297, | |
| "grad_norm": 1.3724550008773804, | |
| "learning_rate": 0.0002, | |
| "loss": 3.2577, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0297000297000297, | |
| "eval_loss": 0.8379923701286316, | |
| "eval_runtime": 177.6782, | |
| "eval_samples_per_second": 11.971, | |
| "eval_steps_per_second": 5.988, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03168003168003168, | |
| "grad_norm": 1.7976691722869873, | |
| "learning_rate": 0.0002, | |
| "loss": 3.2878, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03366003366003366, | |
| "grad_norm": 1.4198904037475586, | |
| "learning_rate": 0.0002, | |
| "loss": 3.3432, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03564003564003564, | |
| "grad_norm": 1.6277859210968018, | |
| "learning_rate": 0.0002, | |
| "loss": 3.8561, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03762003762003762, | |
| "grad_norm": 1.1398273706436157, | |
| "learning_rate": 0.0002, | |
| "loss": 3.5024, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0396000396000396, | |
| "grad_norm": 1.2557786703109741, | |
| "learning_rate": 0.0002, | |
| "loss": 3.0593, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0396000396000396, | |
| "eval_loss": 0.8267537951469421, | |
| "eval_runtime": 177.798, | |
| "eval_samples_per_second": 11.963, | |
| "eval_steps_per_second": 5.984, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.680730813628416e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |