118 lines
3.0 KiB
JSON
118 lines
3.0 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_steps": 2,
|
||
|
|
"global_step": 5,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 0.5484622716903687,
|
||
|
|
"epoch": 0.2,
|
||
|
|
"grad_norm": 4.0961689949035645,
|
||
|
|
"learning_rate": 0.0,
|
||
|
|
"loss": 1.4888970851898193,
|
||
|
|
"mean_token_accuracy": 0.7744107842445374,
|
||
|
|
"num_tokens": 11224.0,
|
||
|
|
"step": 1
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.42378363013267517,
|
||
|
|
"epoch": 0.4,
|
||
|
|
"grad_norm": 5.035952091217041,
|
||
|
|
"learning_rate": 0.0003,
|
||
|
|
"loss": 1.1912707090377808,
|
||
|
|
"mean_token_accuracy": 0.82523512840271,
|
||
|
|
"num_tokens": 22945.0,
|
||
|
|
"step": 2
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4,
|
||
|
|
"eval_entropy": 0.618481457233429,
|
||
|
|
"eval_loss": 1.185321569442749,
|
||
|
|
"eval_mean_token_accuracy": 0.7595234513282776,
|
||
|
|
"eval_num_tokens": 22945.0,
|
||
|
|
"eval_runtime": 1.6133,
|
||
|
|
"eval_samples_per_second": 45.868,
|
||
|
|
"eval_steps_per_second": 1.86,
|
||
|
|
"step": 2
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.4622124433517456,
|
||
|
|
"epoch": 0.6,
|
||
|
|
"grad_norm": 3.1539371013641357,
|
||
|
|
"learning_rate": 0.00025606601717798207,
|
||
|
|
"loss": 0.9553588032722473,
|
||
|
|
"mean_token_accuracy": 0.8058050870895386,
|
||
|
|
"num_tokens": 33789.0,
|
||
|
|
"step": 3
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8048706650733948,
|
||
|
|
"epoch": 0.8,
|
||
|
|
"grad_norm": 1.208950161933899,
|
||
|
|
"learning_rate": 0.00015,
|
||
|
|
"loss": 1.1412327289581299,
|
||
|
|
"mean_token_accuracy": 0.7667560577392578,
|
||
|
|
"num_tokens": 45381.0,
|
||
|
|
"step": 4
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8,
|
||
|
|
"eval_entropy": 0.7176829973856608,
|
||
|
|
"eval_loss": 0.9810225963592529,
|
||
|
|
"eval_mean_token_accuracy": 0.7963984409968058,
|
||
|
|
"eval_num_tokens": 45381.0,
|
||
|
|
"eval_runtime": 1.614,
|
||
|
|
"eval_samples_per_second": 45.85,
|
||
|
|
"eval_steps_per_second": 1.859,
|
||
|
|
"step": 4
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.6132624745368958,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 1.6804311275482178,
|
||
|
|
"learning_rate": 4.3933982822017876e-05,
|
||
|
|
"loss": 0.9730833768844604,
|
||
|
|
"mean_token_accuracy": 0.8212560415267944,
|
||
|
|
"num_tokens": 49937.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.0,
|
||
|
|
"eval_entropy": 0.7293926477432251,
|
||
|
|
"eval_loss": 0.9753875732421875,
|
||
|
|
"eval_mean_token_accuracy": 0.7981735070546468,
|
||
|
|
"eval_num_tokens": 49937.0,
|
||
|
|
"eval_runtime": 1.6137,
|
||
|
|
"eval_samples_per_second": 45.856,
|
||
|
|
"eval_steps_per_second": 1.859,
|
||
|
|
"step": 5
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 1,
|
||
|
|
"max_steps": 5,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 1,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 194982543360000.0,
|
||
|
|
"train_batch_size": 32,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|