|
{ |
|
"best_metric": 1.1260673999786377, |
|
"best_model_checkpoint": "./outputs/checkpoint-1200", |
|
"epoch": 1.6, |
|
"eval_steps": 100, |
|
"global_step": 1200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1592, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.2453653812408447, |
|
"eval_runtime": 180.2468, |
|
"eval_samples_per_second": 10.708, |
|
"eval_steps_per_second": 1.343, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 1.022, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 1.2181000709533691, |
|
"eval_runtime": 176.9082, |
|
"eval_samples_per_second": 10.91, |
|
"eval_steps_per_second": 1.368, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 1.0046, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.2017920017242432, |
|
"eval_runtime": 176.9998, |
|
"eval_samples_per_second": 10.904, |
|
"eval_steps_per_second": 1.367, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9924, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.1916158199310303, |
|
"eval_runtime": 177.494, |
|
"eval_samples_per_second": 10.874, |
|
"eval_steps_per_second": 1.363, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9773, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.1772679090499878, |
|
"eval_runtime": 193.3709, |
|
"eval_samples_per_second": 9.981, |
|
"eval_steps_per_second": 1.251, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9722, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"eval_loss": 1.1649450063705444, |
|
"eval_runtime": 190.0877, |
|
"eval_samples_per_second": 10.153, |
|
"eval_steps_per_second": 1.273, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9654, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"eval_loss": 1.161731481552124, |
|
"eval_runtime": 177.4185, |
|
"eval_samples_per_second": 10.878, |
|
"eval_steps_per_second": 1.364, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9511, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"eval_loss": 1.1482728719711304, |
|
"eval_runtime": 177.4285, |
|
"eval_samples_per_second": 10.878, |
|
"eval_steps_per_second": 1.364, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9396, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"eval_loss": 1.143031358718872, |
|
"eval_runtime": 177.3006, |
|
"eval_samples_per_second": 10.885, |
|
"eval_steps_per_second": 1.365, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9319, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.33, |
|
"eval_loss": 1.136294960975647, |
|
"eval_runtime": 177.4158, |
|
"eval_samples_per_second": 10.878, |
|
"eval_steps_per_second": 1.364, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9393, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 1.47, |
|
"eval_loss": 1.1321903467178345, |
|
"eval_runtime": 177.2509, |
|
"eval_samples_per_second": 10.889, |
|
"eval_steps_per_second": 1.365, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.0002, |
|
"loss": 0.9282, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"eval_loss": 1.1260673999786377, |
|
"eval_runtime": 177.157, |
|
"eval_samples_per_second": 10.894, |
|
"eval_steps_per_second": 1.366, |
|
"step": 1200 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 2250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 8.96699552329728e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|