| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000646629765661373, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.2932595313227458e-05, | |
| "eval_loss": 1.2712680101394653, | |
| "eval_runtime": 2436.9276, | |
| "eval_samples_per_second": 13.36, | |
| "eval_steps_per_second": 6.68, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.46629765661373e-05, | |
| "grad_norm": 1.2175859212875366, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1907, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001293259531322746, | |
| "grad_norm": 1.4099855422973633, | |
| "learning_rate": 0.0001, | |
| "loss": 0.9698, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0001293259531322746, | |
| "eval_loss": 0.6086933016777039, | |
| "eval_runtime": 2466.1818, | |
| "eval_samples_per_second": 13.202, | |
| "eval_steps_per_second": 6.601, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00019398892969841187, | |
| "grad_norm": 0.8784182667732239, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3641, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002586519062645492, | |
| "grad_norm": 1.0158741474151611, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1668, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0002586519062645492, | |
| "eval_loss": 0.0934409499168396, | |
| "eval_runtime": 2461.0672, | |
| "eval_samples_per_second": 13.229, | |
| "eval_steps_per_second": 6.615, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0003233148828306865, | |
| "grad_norm": 0.8833733201026917, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1013, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00038797785939682374, | |
| "grad_norm": 0.4033607244491577, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0561, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00038797785939682374, | |
| "eval_loss": 0.04285094514489174, | |
| "eval_runtime": 2462.534, | |
| "eval_samples_per_second": 13.221, | |
| "eval_steps_per_second": 6.611, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00045264083596296105, | |
| "grad_norm": 0.1996477246284485, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0403, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0005173038125290984, | |
| "grad_norm": 0.30227357149124146, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0305, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0005173038125290984, | |
| "eval_loss": 0.029047120362520218, | |
| "eval_runtime": 2461.24, | |
| "eval_samples_per_second": 13.228, | |
| "eval_steps_per_second": 6.614, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0005819667890952356, | |
| "grad_norm": 0.20860296487808228, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0223, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.000646629765661373, | |
| "grad_norm": 0.15605232119560242, | |
| "learning_rate": 0.0, | |
| "loss": 0.0191, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.000646629765661373, | |
| "eval_loss": 0.027523523196578026, | |
| "eval_runtime": 2463.3601, | |
| "eval_samples_per_second": 13.217, | |
| "eval_steps_per_second": 6.608, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8143670712729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |