| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.003770810158562567, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.541620317125135e-05, | |
| "eval_loss": 1.8562190532684326, | |
| "eval_runtime": 900.2586, | |
| "eval_samples_per_second": 6.203, | |
| "eval_steps_per_second": 3.101, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003770810158562567, | |
| "grad_norm": 4.088282108306885, | |
| "learning_rate": 5e-05, | |
| "loss": 7.7757, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0007541620317125134, | |
| "grad_norm": 5.26944637298584, | |
| "learning_rate": 0.0001, | |
| "loss": 6.9662, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007541620317125134, | |
| "eval_loss": 1.3146437406539917, | |
| "eval_runtime": 903.0345, | |
| "eval_samples_per_second": 6.184, | |
| "eval_steps_per_second": 3.092, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0011312430475687702, | |
| "grad_norm": 3.774066209793091, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 4.1968, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0015083240634250269, | |
| "grad_norm": 4.928558349609375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015083240634250269, | |
| "eval_loss": 0.7486514449119568, | |
| "eval_runtime": 903.8279, | |
| "eval_samples_per_second": 6.178, | |
| "eval_steps_per_second": 3.089, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0018854050792812835, | |
| "grad_norm": 4.04644250869751, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.8283, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0022624860951375404, | |
| "grad_norm": 3.4365930557250977, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6388, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022624860951375404, | |
| "eval_loss": 0.6180438995361328, | |
| "eval_runtime": 908.4724, | |
| "eval_samples_per_second": 6.147, | |
| "eval_steps_per_second": 3.073, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002639567110993797, | |
| "grad_norm": 3.5889577865600586, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.4266, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0030166481268500537, | |
| "grad_norm": 2.860438823699951, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4012, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0030166481268500537, | |
| "eval_loss": 0.5868576765060425, | |
| "eval_runtime": 906.6667, | |
| "eval_samples_per_second": 6.159, | |
| "eval_steps_per_second": 3.079, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0033937291427063106, | |
| "grad_norm": 3.215632915496826, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1886, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.003770810158562567, | |
| "grad_norm": 3.213798761367798, | |
| "learning_rate": 0.0, | |
| "loss": 2.2431, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.003770810158562567, | |
| "eval_loss": 0.5820906162261963, | |
| "eval_runtime": 910.8714, | |
| "eval_samples_per_second": 6.13, | |
| "eval_steps_per_second": 3.065, | |
| "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": 2.845673344991232e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |