| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6016540317022743, | |
| "eval_steps": 291, | |
| "global_step": 873, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06891798759476224, | |
| "grad_norm": 2056.53857421875, | |
| "learning_rate": 9.88326321974139e-06, | |
| "loss": 0.6821, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13783597518952448, | |
| "grad_norm": 1819.6336669921875, | |
| "learning_rate": 9.53850386931162e-06, | |
| "loss": 0.6584, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2005513439007581, | |
| "eval_accuracy": 0.6663206128732011, | |
| "eval_loss": 0.6131747961044312, | |
| "eval_runtime": 482.559, | |
| "eval_samples_per_second": 173.662, | |
| "eval_steps_per_second": 21.709, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.2067539627842867, | |
| "grad_norm": 1910.1011962890625, | |
| "learning_rate": 8.981820387323976e-06, | |
| "loss": 0.6434, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.27567195037904896, | |
| "grad_norm": 1810.4771728515625, | |
| "learning_rate": 8.239206948702616e-06, | |
| "loss": 0.6385, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.34458993797381116, | |
| "grad_norm": 1388.5435791015625, | |
| "learning_rate": 7.345339674168113e-06, | |
| "loss": 0.6248, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4011026878015162, | |
| "eval_accuracy": 0.6850433163886304, | |
| "eval_loss": 0.5890468955039978, | |
| "eval_runtime": 481.5926, | |
| "eval_samples_per_second": 174.01, | |
| "eval_steps_per_second": 21.753, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.4135079255685734, | |
| "grad_norm": 967.0018310546875, | |
| "learning_rate": 6.341957438763544e-06, | |
| "loss": 0.6262, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4824259131633356, | |
| "grad_norm": 1204.761474609375, | |
| "learning_rate": 5.275912887100837e-06, | |
| "loss": 0.6285, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.5513439007580979, | |
| "grad_norm": 1077.1644287109375, | |
| "learning_rate": 4.1969846626093244e-06, | |
| "loss": 0.6203, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.6016540317022743, | |
| "eval_accuracy": 0.6804610868475692, | |
| "eval_loss": 0.5938988327980042, | |
| "eval_runtime": 481.4972, | |
| "eval_samples_per_second": 174.045, | |
| "eval_steps_per_second": 21.757, | |
| "step": 873 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 1451, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 291, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |