| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 200, | |
| "global_step": 2138, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.09354536950420954, | |
| "eval_accuracy": 0.5675198587819947, | |
| "eval_loss": 0.2734091877937317, | |
| "eval_runtime": 34.6483, | |
| "eval_samples_per_second": 32.7, | |
| "eval_steps_per_second": 4.098, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.18709073900841908, | |
| "eval_accuracy": 0.5931156222418358, | |
| "eval_loss": 0.26319071650505066, | |
| "eval_runtime": 34.4168, | |
| "eval_samples_per_second": 32.92, | |
| "eval_steps_per_second": 4.126, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.23386342376052385, | |
| "grad_norm": 1.4175031185150146, | |
| "learning_rate": 3.8306828811973814e-05, | |
| "loss": 0.3013, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.2806361085126286, | |
| "eval_accuracy": 0.6531332744924978, | |
| "eval_loss": 0.23808303475379944, | |
| "eval_runtime": 34.3229, | |
| "eval_samples_per_second": 33.01, | |
| "eval_steps_per_second": 4.137, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.37418147801683815, | |
| "eval_accuracy": 0.6813768755516328, | |
| "eval_loss": 0.23240724205970764, | |
| "eval_runtime": 34.4109, | |
| "eval_samples_per_second": 32.926, | |
| "eval_steps_per_second": 4.127, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.4677268475210477, | |
| "grad_norm": 1.147978663444519, | |
| "learning_rate": 2.6613657623947615e-05, | |
| "loss": 0.2601, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4677268475210477, | |
| "eval_accuracy": 0.7087378640776699, | |
| "eval_loss": 0.22413863241672516, | |
| "eval_runtime": 34.4403, | |
| "eval_samples_per_second": 32.898, | |
| "eval_steps_per_second": 4.123, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5612722170252572, | |
| "eval_accuracy": 0.7228596646072374, | |
| "eval_loss": 0.21633104979991913, | |
| "eval_runtime": 34.4165, | |
| "eval_samples_per_second": 32.92, | |
| "eval_steps_per_second": 4.126, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6548175865294668, | |
| "eval_accuracy": 0.7299205648720212, | |
| "eval_loss": 0.2173129767179489, | |
| "eval_runtime": 34.4021, | |
| "eval_samples_per_second": 32.934, | |
| "eval_steps_per_second": 4.128, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.7015902712815716, | |
| "grad_norm": 1.139875054359436, | |
| "learning_rate": 1.492048643592142e-05, | |
| "loss": 0.2511, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7483629560336763, | |
| "eval_accuracy": 0.7343336275375111, | |
| "eval_loss": 0.21151894330978394, | |
| "eval_runtime": 34.2231, | |
| "eval_samples_per_second": 33.106, | |
| "eval_steps_per_second": 4.149, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.8419083255378859, | |
| "eval_accuracy": 0.7387466902030009, | |
| "eval_loss": 0.20728972554206848, | |
| "eval_runtime": 34.4015, | |
| "eval_samples_per_second": 32.935, | |
| "eval_steps_per_second": 4.128, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "grad_norm": 1.2337602376937866, | |
| "learning_rate": 3.2273152478952295e-06, | |
| "loss": 0.2369, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9354536950420954, | |
| "eval_accuracy": 0.7405119152691968, | |
| "eval_loss": 0.2070828378200531, | |
| "eval_runtime": 34.3972, | |
| "eval_samples_per_second": 32.939, | |
| "eval_steps_per_second": 4.128, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 2138, | |
| "total_flos": 4500493926531072.0, | |
| "train_loss": 0.2609621320961791, | |
| "train_runtime": 2347.8803, | |
| "train_samples_per_second": 7.285, | |
| "train_steps_per_second": 0.911 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2138, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4500493926531072.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |