| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.718562874251497, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.023952095808383235, | |
| "eval_loss": 0.3685842752456665, | |
| "eval_runtime": 1.3724, | |
| "eval_samples_per_second": 13.115, | |
| "eval_steps_per_second": 6.558, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0718562874251497, | |
| "grad_norm": 2.380784034729004, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3711, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1437125748502994, | |
| "grad_norm": 3.242056369781494, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4049, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.19161676646706588, | |
| "eval_loss": 0.10704904049634933, | |
| "eval_runtime": 1.3753, | |
| "eval_samples_per_second": 13.088, | |
| "eval_steps_per_second": 6.544, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2155688622754491, | |
| "grad_norm": 1.6441341638565063, | |
| "learning_rate": 0.00018, | |
| "loss": 0.6681, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2874251497005988, | |
| "grad_norm": 0.5979686975479126, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 0.1314, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.3592814371257485, | |
| "grad_norm": 0.0612233504652977, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.011, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.38323353293413176, | |
| "eval_loss": 0.0003671805025078356, | |
| "eval_runtime": 1.38, | |
| "eval_samples_per_second": 13.043, | |
| "eval_steps_per_second": 6.522, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.4311377245508982, | |
| "grad_norm": 0.03475990891456604, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 0.0015, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5029940119760479, | |
| "grad_norm": 0.02437620423734188, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.001, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.5748502994011976, | |
| "grad_norm": 0.0082920016720891, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.0008, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5748502994011976, | |
| "eval_loss": 0.00020082775154151022, | |
| "eval_runtime": 1.3888, | |
| "eval_samples_per_second": 12.961, | |
| "eval_steps_per_second": 6.48, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.6467065868263473, | |
| "grad_norm": 0.013241025619208813, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.0006, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.718562874251497, | |
| "grad_norm": 0.10441137105226517, | |
| "learning_rate": 0.0, | |
| "loss": 0.0011, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 70, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9772495452241920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |