| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00823799569564725, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.118997847823624e-05, | |
| "eval_loss": 1.3292065858840942, | |
| "eval_runtime": 269.7834, | |
| "eval_samples_per_second": 37.893, | |
| "eval_steps_per_second": 18.949, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00041189978478236243, | |
| "grad_norm": 1.1009160280227661, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2284, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008237995695647249, | |
| "grad_norm": 0.706173300743103, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0498, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0012356993543470873, | |
| "grad_norm": 0.7616959810256958, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0403, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016475991391294497, | |
| "grad_norm": 0.9027200937271118, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0141, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0020594989239118124, | |
| "grad_norm": 0.8844203352928162, | |
| "learning_rate": 0.0002, | |
| "loss": 0.978, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0020594989239118124, | |
| "eval_loss": 0.989996612071991, | |
| "eval_runtime": 269.6524, | |
| "eval_samples_per_second": 37.912, | |
| "eval_steps_per_second": 18.958, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0024713987086941746, | |
| "grad_norm": 0.9188791513442993, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9934, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0028832984934765373, | |
| "grad_norm": 0.7914915680885315, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9846, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0032951982782588995, | |
| "grad_norm": 0.796777069568634, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9583, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.003707098063041262, | |
| "grad_norm": 0.7085840702056885, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8841, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.004118997847823625, | |
| "grad_norm": 0.766033947467804, | |
| "learning_rate": 0.0002, | |
| "loss": 0.938, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004118997847823625, | |
| "eval_loss": 0.940765917301178, | |
| "eval_runtime": 270.1464, | |
| "eval_samples_per_second": 37.842, | |
| "eval_steps_per_second": 18.923, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.004530897632605987, | |
| "grad_norm": 0.8813052177429199, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9171, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.004942797417388349, | |
| "grad_norm": 0.8220875263214111, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9411, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.005354697202170712, | |
| "grad_norm": 0.7601115107536316, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9324, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.0057665969869530745, | |
| "grad_norm": 0.7757460474967957, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9055, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.006178496771735437, | |
| "grad_norm": 0.7860616445541382, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8872, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006178496771735437, | |
| "eval_loss": 0.9218949675559998, | |
| "eval_runtime": 270.9263, | |
| "eval_samples_per_second": 37.734, | |
| "eval_steps_per_second": 18.869, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.006590396556517799, | |
| "grad_norm": 0.7156699895858765, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8475, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.007002296341300162, | |
| "grad_norm": 0.7343199849128723, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9222, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.007414196126082524, | |
| "grad_norm": 1.0209944248199463, | |
| "learning_rate": 0.0002, | |
| "loss": 0.8851, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.007826095910864887, | |
| "grad_norm": 0.903324544429779, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9177, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.00823799569564725, | |
| "grad_norm": 0.8378692269325256, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9269, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.00823799569564725, | |
| "eval_loss": 0.9066545367240906, | |
| "eval_runtime": 270.1918, | |
| "eval_samples_per_second": 37.836, | |
| "eval_steps_per_second": 18.92, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.6400973299712e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |