| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02224694104560623, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007415647015202076, | |
| "eval_loss": 2.5420961380004883, | |
| "eval_runtime": 79.8279, | |
| "eval_samples_per_second": 7.115, | |
| "eval_steps_per_second": 3.558, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002224694104560623, | |
| "grad_norm": 5.313490867614746, | |
| "learning_rate": 6e-05, | |
| "loss": 10.1044, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004449388209121246, | |
| "grad_norm": 7.235334873199463, | |
| "learning_rate": 0.00012, | |
| "loss": 9.4141, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005932517612161661, | |
| "eval_loss": 1.5158597230911255, | |
| "eval_runtime": 81.2804, | |
| "eval_samples_per_second": 6.988, | |
| "eval_steps_per_second": 3.494, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006674082313681869, | |
| "grad_norm": 10.101544380187988, | |
| "learning_rate": 0.00018, | |
| "loss": 7.9929, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008898776418242492, | |
| "grad_norm": 5.074840545654297, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.8182, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011123470522803115, | |
| "grad_norm": 98.48111724853516, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 1.2382, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011865035224323322, | |
| "eval_loss": 0.35880428552627563, | |
| "eval_runtime": 81.1112, | |
| "eval_samples_per_second": 7.003, | |
| "eval_steps_per_second": 3.501, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013348164627363738, | |
| "grad_norm": 12.51295280456543, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.2371, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01557285873192436, | |
| "grad_norm": 102.7032241821289, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 0.698, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017797552836484983, | |
| "grad_norm": 6.82338809967041, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 0.9465, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.017797552836484983, | |
| "eval_loss": 0.16899226605892181, | |
| "eval_runtime": 81.3702, | |
| "eval_samples_per_second": 6.98, | |
| "eval_steps_per_second": 3.49, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020022246941045607, | |
| "grad_norm": 2.1208465099334717, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 0.5396, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02224694104560623, | |
| "grad_norm": 0.6668184995651245, | |
| "learning_rate": 0.0, | |
| "loss": 0.4415, | |
| "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": 9801969665310720.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |