| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0004968944099378882, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.6563146997929607e-05, | |
| "eval_loss": 1.8955724239349365, | |
| "eval_runtime": 3032.4894, | |
| "eval_samples_per_second": 8.383, | |
| "eval_steps_per_second": 4.192, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.968944099378882e-05, | |
| "grad_norm": 0.5266929268836975, | |
| "learning_rate": 6e-05, | |
| "loss": 1.9783, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.937888198757764e-05, | |
| "grad_norm": 0.6295239329338074, | |
| "learning_rate": 0.00012, | |
| "loss": 1.9468, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00013250517598343685, | |
| "eval_loss": 1.696730136871338, | |
| "eval_runtime": 3035.6554, | |
| "eval_samples_per_second": 8.374, | |
| "eval_steps_per_second": 4.187, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00014906832298136645, | |
| "grad_norm": 0.3753492534160614, | |
| "learning_rate": 0.00018, | |
| "loss": 1.6692, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00019875776397515528, | |
| "grad_norm": 0.7200483083724976, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 1.6255, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002484472049689441, | |
| "grad_norm": 0.3964109420776367, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.6641, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0002650103519668737, | |
| "eval_loss": 1.5444958209991455, | |
| "eval_runtime": 3034.0296, | |
| "eval_samples_per_second": 8.379, | |
| "eval_steps_per_second": 4.189, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0002981366459627329, | |
| "grad_norm": 0.33579447865486145, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.6568, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00034782608695652176, | |
| "grad_norm": 0.38937875628471375, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.5313, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00039751552795031056, | |
| "grad_norm": 0.29954230785369873, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 1.4734, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00039751552795031056, | |
| "eval_loss": 1.506805658340454, | |
| "eval_runtime": 3034.2082, | |
| "eval_samples_per_second": 8.378, | |
| "eval_steps_per_second": 4.189, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00044720496894409936, | |
| "grad_norm": 0.2913510203361511, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.4762, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0004968944099378882, | |
| "grad_norm": 0.28156813979148865, | |
| "learning_rate": 0.0, | |
| "loss": 1.5092, | |
| "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": 4939038012211200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |