| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006046710841248646, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.0155702804162153e-05, | |
| "eval_loss": 2.4655165672302246, | |
| "eval_runtime": 710.5136, | |
| "eval_samples_per_second": 29.401, | |
| "eval_steps_per_second": 14.701, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.0467108412486456e-05, | |
| "grad_norm": 58.87119674682617, | |
| "learning_rate": 6e-05, | |
| "loss": 9.9797, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012093421682497291, | |
| "grad_norm": 335.19183349609375, | |
| "learning_rate": 0.00012, | |
| "loss": 10.5461, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016124562243329722, | |
| "eval_loss": 2.297055244445801, | |
| "eval_runtime": 710.4042, | |
| "eval_samples_per_second": 29.406, | |
| "eval_steps_per_second": 14.703, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00018140132523745937, | |
| "grad_norm": 3.957228183746338, | |
| "learning_rate": 0.00018, | |
| "loss": 10.2177, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00024186843364994582, | |
| "grad_norm": 305.9400634765625, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 8.9782, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0003023355420624323, | |
| "grad_norm": 197.7496795654297, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 8.913, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00032249124486659445, | |
| "eval_loss": 1.9983162879943848, | |
| "eval_runtime": 710.6411, | |
| "eval_samples_per_second": 29.396, | |
| "eval_steps_per_second": 14.698, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00036280265047491873, | |
| "grad_norm": 5.757598400115967, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 9.1496, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0004232697588874052, | |
| "grad_norm": 4.392923355102539, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 7.797, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.00048373686729989165, | |
| "grad_norm": 1135.9619140625, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 8.145, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00048373686729989165, | |
| "eval_loss": 1.8751978874206543, | |
| "eval_runtime": 710.7939, | |
| "eval_samples_per_second": 29.39, | |
| "eval_steps_per_second": 14.695, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005442039757123781, | |
| "grad_norm": 480.12786865234375, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 6.7705, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0006046710841248646, | |
| "grad_norm": 4.261571407318115, | |
| "learning_rate": 0.0, | |
| "loss": 7.6497, | |
| "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": 538483504447488.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |