| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.009523809523809525, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00019047619047619048, | |
| "eval_loss": 4.401525974273682, | |
| "eval_runtime": 129.3176, | |
| "eval_samples_per_second": 17.097, | |
| "eval_steps_per_second": 8.553, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009523809523809524, | |
| "grad_norm": 6.0887322425842285, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2216, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0019047619047619048, | |
| "grad_norm": 6.629170894622803, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4607, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0019047619047619048, | |
| "eval_loss": 1.6496787071228027, | |
| "eval_runtime": 130.0353, | |
| "eval_samples_per_second": 17.003, | |
| "eval_steps_per_second": 8.505, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002857142857142857, | |
| "grad_norm": 0.5109394788742065, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.5315, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0038095238095238095, | |
| "grad_norm": 0.10917386412620544, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0126, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0038095238095238095, | |
| "eval_loss": 0.045543376356363297, | |
| "eval_runtime": 129.8082, | |
| "eval_samples_per_second": 17.033, | |
| "eval_steps_per_second": 8.52, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.004761904761904762, | |
| "grad_norm": 0.0012036367552354932, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0006, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.005714285714285714, | |
| "grad_norm": 0.0002805074327625334, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.005714285714285714, | |
| "eval_loss": 0.0358709990978241, | |
| "eval_runtime": 130.2297, | |
| "eval_samples_per_second": 16.978, | |
| "eval_steps_per_second": 8.493, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.006666666666666667, | |
| "grad_norm": 0.0003203921078238636, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0915, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.007619047619047619, | |
| "grad_norm": 0.002745690755546093, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0003, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.007619047619047619, | |
| "eval_loss": 0.03260380029678345, | |
| "eval_runtime": 130.4906, | |
| "eval_samples_per_second": 16.944, | |
| "eval_steps_per_second": 8.476, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.008571428571428572, | |
| "grad_norm": 0.0005702447961084545, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.009523809523809525, | |
| "grad_norm": 0.01588163711130619, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.009523809523809525, | |
| "eval_loss": 0.0321432463824749, | |
| "eval_runtime": 130.4634, | |
| "eval_samples_per_second": 16.947, | |
| "eval_steps_per_second": 8.477, | |
| "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": 8225102336360448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |