| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0062791062738736855, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00020930354246245618, | |
| "eval_loss": 1.9980238676071167, | |
| "eval_runtime": 382.1313, | |
| "eval_samples_per_second": 5.265, | |
| "eval_steps_per_second": 2.633, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006279106273873685, | |
| "grad_norm": 0.5501781105995178, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9814, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001255821254774737, | |
| "grad_norm": 0.6605830788612366, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9938, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0016744283396996494, | |
| "eval_loss": 1.7701950073242188, | |
| "eval_runtime": 384.4451, | |
| "eval_samples_per_second": 5.234, | |
| "eval_steps_per_second": 2.617, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0018837318821621056, | |
| "grad_norm": 0.38709595799446106, | |
| "learning_rate": 0.00018, | |
| "loss": 1.8724, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002511642509549474, | |
| "grad_norm": 0.5700718760490417, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.7668, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0031395531369368427, | |
| "grad_norm": 0.4456750154495239, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.7042, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003348856679399299, | |
| "eval_loss": 1.709465742111206, | |
| "eval_runtime": 384.5649, | |
| "eval_samples_per_second": 5.232, | |
| "eval_steps_per_second": 2.616, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.003767463764324211, | |
| "grad_norm": 0.29748132824897766, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6943, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0043953743917115795, | |
| "grad_norm": 0.296750545501709, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.6972, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005023285019098948, | |
| "grad_norm": 0.3044898211956024, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.6936, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005023285019098948, | |
| "eval_loss": 1.6853996515274048, | |
| "eval_runtime": 385.0934, | |
| "eval_samples_per_second": 5.225, | |
| "eval_steps_per_second": 2.612, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.005651195646486317, | |
| "grad_norm": 0.2489960789680481, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.6719, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0062791062738736855, | |
| "grad_norm": 0.2668619155883789, | |
| "learning_rate": 0.0, | |
| "loss": 1.6954, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.512252792373248e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |