| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010077851402081077, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.0155702804162153e-05, | |
| "eval_loss": 1.8410059213638306, | |
| "eval_runtime": 1911.8733, | |
| "eval_samples_per_second": 10.926, | |
| "eval_steps_per_second": 5.463, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00010077851402081077, | |
| "grad_norm": 1.9838496446609497, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00020155702804162154, | |
| "grad_norm": 1.3555948734283447, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6573, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00020155702804162154, | |
| "eval_loss": 1.4620121717453003, | |
| "eval_runtime": 1917.889, | |
| "eval_samples_per_second": 10.892, | |
| "eval_steps_per_second": 5.446, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003023355420624323, | |
| "grad_norm": 1.3019169569015503, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.163, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004031140560832431, | |
| "grad_norm": 0.7878373861312866, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3866, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004031140560832431, | |
| "eval_loss": 1.1855676174163818, | |
| "eval_runtime": 1921.0938, | |
| "eval_samples_per_second": 10.874, | |
| "eval_steps_per_second": 5.437, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0005038925701040538, | |
| "grad_norm": 1.455486536026001, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.3197, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0006046710841248646, | |
| "grad_norm": 1.0628057718276978, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1808, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006046710841248646, | |
| "eval_loss": 1.1275780200958252, | |
| "eval_runtime": 1917.7949, | |
| "eval_samples_per_second": 10.893, | |
| "eval_steps_per_second": 5.446, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0007054495981456754, | |
| "grad_norm": 0.5723454356193542, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3362, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0008062281121664861, | |
| "grad_norm": 1.378598690032959, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8891, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008062281121664861, | |
| "eval_loss": 1.10456383228302, | |
| "eval_runtime": 1915.9106, | |
| "eval_samples_per_second": 10.903, | |
| "eval_steps_per_second": 5.452, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0009070066261872969, | |
| "grad_norm": 0.817628026008606, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1041, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0010077851402081077, | |
| "grad_norm": 1.2205736637115479, | |
| "learning_rate": 0.0, | |
| "loss": 1.131, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010077851402081077, | |
| "eval_loss": 1.10031259059906, | |
| "eval_runtime": 1922.4649, | |
| "eval_samples_per_second": 10.866, | |
| "eval_steps_per_second": 5.433, | |
| "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": 1.2761993312206848e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |