| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.010011680293675955, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003337226764558652, | |
| "eval_loss": 1.3645532131195068, | |
| "eval_runtime": 321.5008, | |
| "eval_samples_per_second": 3.925, | |
| "eval_steps_per_second": 1.963, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0010011680293675956, | |
| "grad_norm": 0.6333549618721008, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3858, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002002336058735191, | |
| "grad_norm": 0.6915407180786133, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3306, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0026697814116469214, | |
| "eval_loss": 1.2134857177734375, | |
| "eval_runtime": 323.5478, | |
| "eval_samples_per_second": 3.901, | |
| "eval_steps_per_second": 1.95, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0030035040881027865, | |
| "grad_norm": 0.7062073349952698, | |
| "learning_rate": 0.00018, | |
| "loss": 1.2628, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004004672117470382, | |
| "grad_norm": 0.5901994109153748, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.1515, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005005840146837978, | |
| "grad_norm": 0.41187232732772827, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.1306, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.005339562823293843, | |
| "eval_loss": 1.0811344385147095, | |
| "eval_runtime": 323.2239, | |
| "eval_samples_per_second": 3.904, | |
| "eval_steps_per_second": 1.952, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006007008176205573, | |
| "grad_norm": 0.4243963062763214, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.0679, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007008176205573168, | |
| "grad_norm": 0.3598477840423584, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.0699, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008009344234940765, | |
| "grad_norm": 0.3618379831314087, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.0099, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008009344234940765, | |
| "eval_loss": 1.0488207340240479, | |
| "eval_runtime": 323.4023, | |
| "eval_samples_per_second": 3.902, | |
| "eval_steps_per_second": 1.951, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00901051226430836, | |
| "grad_norm": 0.4253661334514618, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.0443, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.010011680293675955, | |
| "grad_norm": 0.3688424825668335, | |
| "learning_rate": 0.0, | |
| "loss": 1.0724, | |
| "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": 2.2163882596368384e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |