| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.020167389331451045, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004033477866290209, | |
| "eval_loss": 1.4710214138031006, | |
| "eval_runtime": 78.2284, | |
| "eval_samples_per_second": 13.346, | |
| "eval_steps_per_second": 6.673, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0020167389331451043, | |
| "grad_norm": 27.991483688354492, | |
| "learning_rate": 5e-05, | |
| "loss": 6.1142, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0040334778662902086, | |
| "grad_norm": 36.424503326416016, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5091, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0040334778662902086, | |
| "eval_loss": 0.7015925645828247, | |
| "eval_runtime": 82.5957, | |
| "eval_samples_per_second": 12.64, | |
| "eval_steps_per_second": 6.32, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006050216799435313, | |
| "grad_norm": 26.486326217651367, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1914, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008066955732580417, | |
| "grad_norm": 63.64850997924805, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.8607, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008066955732580417, | |
| "eval_loss": 0.11317463964223862, | |
| "eval_runtime": 83.5211, | |
| "eval_samples_per_second": 12.5, | |
| "eval_steps_per_second": 6.25, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010083694665725522, | |
| "grad_norm": 6.259247779846191, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5215, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.012100433598870626, | |
| "grad_norm": 5.542822360992432, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3276, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.012100433598870626, | |
| "eval_loss": 0.06903474032878876, | |
| "eval_runtime": 83.5102, | |
| "eval_samples_per_second": 12.501, | |
| "eval_steps_per_second": 6.251, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01411717253201573, | |
| "grad_norm": 7.3345561027526855, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.15, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016133911465160834, | |
| "grad_norm": 5.170049667358398, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1905, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016133911465160834, | |
| "eval_loss": 0.04502296447753906, | |
| "eval_runtime": 83.4773, | |
| "eval_samples_per_second": 12.506, | |
| "eval_steps_per_second": 6.253, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018150650398305938, | |
| "grad_norm": 2.700343132019043, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1927, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.020167389331451045, | |
| "grad_norm": 3.4990785121917725, | |
| "learning_rate": 0.0, | |
| "loss": 0.1571, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.020167389331451045, | |
| "eval_loss": 0.04144294187426567, | |
| "eval_runtime": 83.4741, | |
| "eval_samples_per_second": 12.507, | |
| "eval_steps_per_second": 6.253, | |
| "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": 8763358996070400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |