| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00029059841478564733, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.9059841478564733e-05, | |
| "grad_norm": 3.0797133445739746, | |
| "learning_rate": 2e-05, | |
| "loss": 7.1825, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.9059841478564733e-05, | |
| "eval_loss": 1.8562840223312378, | |
| "eval_runtime": 196.2793, | |
| "eval_samples_per_second": 73.823, | |
| "eval_steps_per_second": 36.912, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.8119682957129466e-05, | |
| "grad_norm": 3.140251874923706, | |
| "learning_rate": 4e-05, | |
| "loss": 7.1964, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.71795244356942e-05, | |
| "grad_norm": 3.4224812984466553, | |
| "learning_rate": 6e-05, | |
| "loss": 9.1258, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.71795244356942e-05, | |
| "eval_loss": 1.8514827489852905, | |
| "eval_runtime": 196.25, | |
| "eval_samples_per_second": 73.834, | |
| "eval_steps_per_second": 36.917, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00011623936591425893, | |
| "grad_norm": 2.0716779232025146, | |
| "learning_rate": 8e-05, | |
| "loss": 7.0046, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00014529920739282366, | |
| "grad_norm": 3.4374592304229736, | |
| "learning_rate": 0.0001, | |
| "loss": 7.0018, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001743590488713884, | |
| "grad_norm": 3.3420591354370117, | |
| "learning_rate": 0.00012, | |
| "loss": 7.1482, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001743590488713884, | |
| "eval_loss": 1.822418451309204, | |
| "eval_runtime": 197.1055, | |
| "eval_samples_per_second": 73.514, | |
| "eval_steps_per_second": 36.757, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00020341889034995313, | |
| "grad_norm": 4.159395694732666, | |
| "learning_rate": 0.00014, | |
| "loss": 8.2937, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00023247873182851786, | |
| "grad_norm": 2.6931440830230713, | |
| "learning_rate": 0.00016, | |
| "loss": 6.9347, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002615385733070826, | |
| "grad_norm": 2.914299726486206, | |
| "learning_rate": 0.00018, | |
| "loss": 8.2373, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002615385733070826, | |
| "eval_loss": 1.7719378471374512, | |
| "eval_runtime": 197.9792, | |
| "eval_samples_per_second": 73.189, | |
| "eval_steps_per_second": 36.595, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00029059841478564733, | |
| "grad_norm": 2.9147603511810303, | |
| "learning_rate": 0.0002, | |
| "loss": 6.7115, | |
| "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": 395864476483584.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |