| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.019790223629527013, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00039580447259054025, | |
| "eval_loss": 1.3191004991531372, | |
| "eval_runtime": 87.2633, | |
| "eval_samples_per_second": 12.193, | |
| "eval_steps_per_second": 6.096, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0019790223629527013, | |
| "grad_norm": 0.6584509015083313, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3175, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003958044725905403, | |
| "grad_norm": 0.5416198372840881, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2596, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.003958044725905403, | |
| "eval_loss": 1.22352933883667, | |
| "eval_runtime": 88.4037, | |
| "eval_samples_per_second": 12.036, | |
| "eval_steps_per_second": 6.018, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005937067088858104, | |
| "grad_norm": 0.6631811261177063, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.1461, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007916089451810805, | |
| "grad_norm": 0.6872115135192871, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0504, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007916089451810805, | |
| "eval_loss": 0.9962456226348877, | |
| "eval_runtime": 88.4825, | |
| "eval_samples_per_second": 12.025, | |
| "eval_steps_per_second": 6.012, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009895111814763506, | |
| "grad_norm": 0.5847287774085999, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.017, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011874134177716208, | |
| "grad_norm": 0.5955860614776611, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9265, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011874134177716208, | |
| "eval_loss": 0.9131612777709961, | |
| "eval_runtime": 88.6617, | |
| "eval_samples_per_second": 12.001, | |
| "eval_steps_per_second": 6.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013853156540668909, | |
| "grad_norm": 0.6309583187103271, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8876, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01583217890362161, | |
| "grad_norm": 0.6236824989318848, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.8796, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01583217890362161, | |
| "eval_loss": 0.8821372389793396, | |
| "eval_runtime": 88.453, | |
| "eval_samples_per_second": 12.029, | |
| "eval_steps_per_second": 6.014, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.017811201266574313, | |
| "grad_norm": 0.4817047119140625, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8854, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.019790223629527013, | |
| "grad_norm": 0.5099672675132751, | |
| "learning_rate": 0.0, | |
| "loss": 0.8664, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.019790223629527013, | |
| "eval_loss": 0.8753272891044617, | |
| "eval_runtime": 88.4937, | |
| "eval_samples_per_second": 12.023, | |
| "eval_steps_per_second": 6.012, | |
| "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": 1.2364810800857088e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |