| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01002004008016032, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001002004008016032, | |
| "grad_norm": 0.34832796454429626, | |
| "learning_rate": 2e-05, | |
| "loss": 5.0781, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001002004008016032, | |
| "eval_loss": 1.245298981666565, | |
| "eval_runtime": 32.1607, | |
| "eval_samples_per_second": 13.091, | |
| "eval_steps_per_second": 6.561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002004008016032064, | |
| "grad_norm": 0.3496541380882263, | |
| "learning_rate": 4e-05, | |
| "loss": 5.1646, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.003006012024048096, | |
| "grad_norm": 0.3487575948238373, | |
| "learning_rate": 6e-05, | |
| "loss": 4.7958, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003006012024048096, | |
| "eval_loss": 1.2446060180664062, | |
| "eval_runtime": 30.9161, | |
| "eval_samples_per_second": 13.618, | |
| "eval_steps_per_second": 6.825, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004008016032064128, | |
| "grad_norm": 0.3600659966468811, | |
| "learning_rate": 8e-05, | |
| "loss": 4.7573, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00501002004008016, | |
| "grad_norm": 0.43822160363197327, | |
| "learning_rate": 0.0001, | |
| "loss": 4.6953, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006012024048096192, | |
| "grad_norm": 0.5357103943824768, | |
| "learning_rate": 0.00012, | |
| "loss": 4.6973, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006012024048096192, | |
| "eval_loss": 1.2071658372879028, | |
| "eval_runtime": 31.0044, | |
| "eval_samples_per_second": 13.579, | |
| "eval_steps_per_second": 6.805, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0070140280561122245, | |
| "grad_norm": 0.6890850067138672, | |
| "learning_rate": 0.00014, | |
| "loss": 4.7609, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.008016032064128256, | |
| "grad_norm": 0.7650081515312195, | |
| "learning_rate": 0.00016, | |
| "loss": 4.4633, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.009018036072144289, | |
| "grad_norm": 1.066926121711731, | |
| "learning_rate": 0.00018, | |
| "loss": 4.3805, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.009018036072144289, | |
| "eval_loss": 1.0714982748031616, | |
| "eval_runtime": 30.8589, | |
| "eval_samples_per_second": 13.643, | |
| "eval_steps_per_second": 6.838, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01002004008016032, | |
| "grad_norm": 1.0714696645736694, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1267, | |
| "step": 10 | |
| } | |
| ], | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6274650262732800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |