| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0013855692957844053, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.6185643192813516e-05, | |
| "eval_loss": 5.59415864944458, | |
| "eval_runtime": 1675.3459, | |
| "eval_samples_per_second": 5.442, | |
| "eval_steps_per_second": 2.721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013855692957844053, | |
| "grad_norm": 9.129727363586426, | |
| "learning_rate": 6e-05, | |
| "loss": 21.9235, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00027711385915688106, | |
| "grad_norm": 12.987714767456055, | |
| "learning_rate": 0.00012, | |
| "loss": 22.9083, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00036948514554250813, | |
| "eval_loss": 4.322031497955322, | |
| "eval_runtime": 1680.7058, | |
| "eval_samples_per_second": 5.425, | |
| "eval_steps_per_second": 2.713, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0004156707887353216, | |
| "grad_norm": 13.042325973510742, | |
| "learning_rate": 0.00018, | |
| "loss": 18.2704, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0005542277183137621, | |
| "grad_norm": 16.739822387695312, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 13.8669, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0006927846478922027, | |
| "grad_norm": 20.34059715270996, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.1309, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0007389702910850163, | |
| "eval_loss": 2.2822928428649902, | |
| "eval_runtime": 1682.0271, | |
| "eval_samples_per_second": 5.42, | |
| "eval_steps_per_second": 2.71, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0008313415774706432, | |
| "grad_norm": 27.60608673095703, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.5489, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0009698985070490838, | |
| "grad_norm": 18.565593719482422, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 7.5356, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0011084554366275242, | |
| "grad_norm": 14.486281394958496, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 7.8155, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0011084554366275242, | |
| "eval_loss": 2.0036540031433105, | |
| "eval_runtime": 1681.4047, | |
| "eval_samples_per_second": 5.422, | |
| "eval_steps_per_second": 2.711, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0012470123662059649, | |
| "grad_norm": 12.505599021911621, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 8.6247, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0013855692957844053, | |
| "grad_norm": 15.81383228302002, | |
| "learning_rate": 0.0, | |
| "loss": 6.7641, | |
| "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": 1.920218563608576e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |