| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007756447547023463, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 8.618275052248293e-05, | |
| "grad_norm": 1.395546317100525, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.618275052248293e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 196.0247, | |
| "eval_samples_per_second": 24.925, | |
| "eval_steps_per_second": 12.463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00017236550104496586, | |
| "grad_norm": 1.01736319065094, | |
| "learning_rate": 4e-05, | |
| "loss": 1.6179, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0002585482515674488, | |
| "grad_norm": 1.0673377513885498, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3225, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002585482515674488, | |
| "eval_loss": NaN, | |
| "eval_runtime": 195.9332, | |
| "eval_samples_per_second": 24.937, | |
| "eval_steps_per_second": 12.469, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003447310020899317, | |
| "grad_norm": 1.5866104364395142, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7591, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004309137526124146, | |
| "grad_norm": 1.2332730293273926, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005170965031348976, | |
| "grad_norm": 1.3664995431900024, | |
| "learning_rate": 0.00012, | |
| "loss": 1.7888, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005170965031348976, | |
| "eval_loss": NaN, | |
| "eval_runtime": 196.0794, | |
| "eval_samples_per_second": 24.918, | |
| "eval_steps_per_second": 12.459, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006032792536573804, | |
| "grad_norm": 1.0203039646148682, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0586, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006894620041798634, | |
| "grad_norm": 1.3906350135803223, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7009, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007756447547023463, | |
| "grad_norm": 2.2116494178771973, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6583, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007756447547023463, | |
| "eval_loss": NaN, | |
| "eval_runtime": 196.0011, | |
| "eval_samples_per_second": 24.928, | |
| "eval_steps_per_second": 12.464, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1025060831232000.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |