| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.016755096341803964, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005585032113934655, | |
| "eval_loss": 1.9188768863677979, | |
| "eval_runtime": 74.7902, | |
| "eval_samples_per_second": 10.082, | |
| "eval_steps_per_second": 5.041, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016755096341803965, | |
| "grad_norm": 0.5450559854507446, | |
| "learning_rate": 3e-05, | |
| "loss": 1.754, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003351019268360793, | |
| "grad_norm": 0.42937543988227844, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7467, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004468025691147724, | |
| "eval_loss": 1.8702775239944458, | |
| "eval_runtime": 73.7319, | |
| "eval_samples_per_second": 10.226, | |
| "eval_steps_per_second": 5.113, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00502652890254119, | |
| "grad_norm": 0.6442775726318359, | |
| "learning_rate": 9e-05, | |
| "loss": 1.7701, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006702038536721586, | |
| "grad_norm": 0.4694407284259796, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 1.7087, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008377548170901982, | |
| "grad_norm": 0.6366439461708069, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8041, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008936051382295447, | |
| "eval_loss": 1.6128548383712769, | |
| "eval_runtime": 73.7525, | |
| "eval_samples_per_second": 10.223, | |
| "eval_steps_per_second": 5.112, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01005305780508238, | |
| "grad_norm": 0.32043302059173584, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.6812, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011728567439262776, | |
| "grad_norm": 0.3746090233325958, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 1.5182, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013404077073443172, | |
| "grad_norm": 0.35193824768066406, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.6265, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013404077073443172, | |
| "eval_loss": 1.5419925451278687, | |
| "eval_runtime": 73.8676, | |
| "eval_samples_per_second": 10.207, | |
| "eval_steps_per_second": 5.104, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015079586707623568, | |
| "grad_norm": 0.34421786665916443, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 1.4906, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.016755096341803964, | |
| "grad_norm": 0.3292273283004761, | |
| "learning_rate": 0.0, | |
| "loss": 1.6185, | |
| "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": 2.094771430490112e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |