| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.01668613382279326, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003337226764558652, | |
| "eval_loss": 1.4693615436553955, | |
| "eval_runtime": 154.5372, | |
| "eval_samples_per_second": 8.166, | |
| "eval_steps_per_second": 4.083, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016686133822793258, | |
| "grad_norm": 1.5695351362228394, | |
| "learning_rate": 5e-05, | |
| "loss": 1.5529, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033372267645586516, | |
| "grad_norm": 1.253214716911316, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4291, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0033372267645586516, | |
| "eval_loss": 1.323049783706665, | |
| "eval_runtime": 155.591, | |
| "eval_samples_per_second": 8.111, | |
| "eval_steps_per_second": 4.056, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005005840146837978, | |
| "grad_norm": 1.1968896389007568, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.2625, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006674453529117303, | |
| "grad_norm": 1.6381624937057495, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0152, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006674453529117303, | |
| "eval_loss": 1.1381220817565918, | |
| "eval_runtime": 155.4963, | |
| "eval_samples_per_second": 8.116, | |
| "eval_steps_per_second": 4.058, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00834306691139663, | |
| "grad_norm": 2.598337173461914, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.8971, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010011680293675955, | |
| "grad_norm": 1.3308476209640503, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0069, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.010011680293675955, | |
| "eval_loss": 1.0423482656478882, | |
| "eval_runtime": 155.7042, | |
| "eval_samples_per_second": 8.105, | |
| "eval_steps_per_second": 4.053, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011680293675955281, | |
| "grad_norm": 1.6983165740966797, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8611, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013348907058234607, | |
| "grad_norm": 1.6252766847610474, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8803, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.013348907058234607, | |
| "eval_loss": 1.0084389448165894, | |
| "eval_runtime": 155.7543, | |
| "eval_samples_per_second": 8.103, | |
| "eval_steps_per_second": 4.051, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015017520440513932, | |
| "grad_norm": 1.2326836585998535, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8597, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01668613382279326, | |
| "grad_norm": 1.4419682025909424, | |
| "learning_rate": 0.0, | |
| "loss": 0.9714, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01668613382279326, | |
| "eval_loss": 1.0037347078323364, | |
| "eval_runtime": 155.2929, | |
| "eval_samples_per_second": 8.127, | |
| "eval_steps_per_second": 4.063, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.84956424814592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |