| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009444654325651681, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00018889308651303362, | |
| "eval_loss": 0.6436558961868286, | |
| "eval_runtime": 309.7106, | |
| "eval_samples_per_second": 7.2, | |
| "eval_steps_per_second": 3.6, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009444654325651682, | |
| "grad_norm": 0.8755938410758972, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3002, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0018889308651303363, | |
| "grad_norm": 0.9676241874694824, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4821, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0018889308651303363, | |
| "eval_loss": 0.6001492142677307, | |
| "eval_runtime": 310.6428, | |
| "eval_samples_per_second": 7.179, | |
| "eval_steps_per_second": 3.589, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0028333962976955043, | |
| "grad_norm": 2.264620780944824, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2726, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0037778617302606727, | |
| "grad_norm": 1.8826525211334229, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8682, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0037778617302606727, | |
| "eval_loss": 0.4691351652145386, | |
| "eval_runtime": 310.6736, | |
| "eval_samples_per_second": 7.178, | |
| "eval_steps_per_second": 3.589, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004722327162825841, | |
| "grad_norm": 1.2390393018722534, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5787, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0056667925953910086, | |
| "grad_norm": 1.221107840538025, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7137, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0056667925953910086, | |
| "eval_loss": 0.4177936911582947, | |
| "eval_runtime": 310.7811, | |
| "eval_samples_per_second": 7.175, | |
| "eval_steps_per_second": 3.588, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0066112580279561765, | |
| "grad_norm": 1.773136019706726, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.4533, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007555723460521345, | |
| "grad_norm": 1.3264466524124146, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6413, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007555723460521345, | |
| "eval_loss": 0.40379035472869873, | |
| "eval_runtime": 310.5742, | |
| "eval_samples_per_second": 7.18, | |
| "eval_steps_per_second": 3.59, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008500188893086513, | |
| "grad_norm": 1.6513358354568481, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.4593, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009444654325651681, | |
| "grad_norm": 2.088416576385498, | |
| "learning_rate": 0.0, | |
| "loss": 1.7247, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009444654325651681, | |
| "eval_loss": 0.4012139141559601, | |
| "eval_runtime": 310.5911, | |
| "eval_samples_per_second": 7.18, | |
| "eval_steps_per_second": 3.59, | |
| "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": 1.3575679546251264e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |