| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008979347500748278, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000299311583358276, | |
| "eval_loss": 10.377535820007324, | |
| "eval_runtime": 13.1279, | |
| "eval_samples_per_second": 107.176, | |
| "eval_steps_per_second": 53.626, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008979347500748278, | |
| "grad_norm": 0.032276831567287445, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3778, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0017958695001496557, | |
| "grad_norm": 0.03204995393753052, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3774, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002394492666866208, | |
| "eval_loss": 10.376775741577148, | |
| "eval_runtime": 12.968, | |
| "eval_samples_per_second": 108.498, | |
| "eval_steps_per_second": 54.287, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0026938042502244837, | |
| "grad_norm": 0.036611057817935944, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3775, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0035917390002993114, | |
| "grad_norm": 0.03667126223444939, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.3771, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004489673750374139, | |
| "grad_norm": 0.04212287440896034, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.3768, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004788985333732416, | |
| "eval_loss": 10.37470531463623, | |
| "eval_runtime": 12.8704, | |
| "eval_samples_per_second": 109.32, | |
| "eval_steps_per_second": 54.699, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.005387608500448967, | |
| "grad_norm": 0.041185591369867325, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.3743, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0062855432505237955, | |
| "grad_norm": 0.04413003474473953, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.3742, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.007183478000598623, | |
| "grad_norm": 0.04242898151278496, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.3731, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007183478000598623, | |
| "eval_loss": 10.373275756835938, | |
| "eval_runtime": 12.7555, | |
| "eval_samples_per_second": 110.305, | |
| "eval_steps_per_second": 55.192, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.008081412750673452, | |
| "grad_norm": 0.046601515263319016, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.3728, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008979347500748278, | |
| "grad_norm": 0.04899485409259796, | |
| "learning_rate": 0.0, | |
| "loss": 10.3722, | |
| "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": 1569073397760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |