155 lines
3.6 KiB
JSON
155 lines
3.6 KiB
JSON
{
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 1.0,
|
|
"eval_steps": 500,
|
|
"global_step": 1689,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.05920663114268798,
|
|
"grad_norm": 58774.96875,
|
|
"learning_rate": 4.70396684428656e-05,
|
|
"loss": 0.767,
|
|
"step": 100
|
|
},
|
|
{
|
|
"epoch": 0.11841326228537596,
|
|
"grad_norm": 84537.3046875,
|
|
"learning_rate": 4.40793368857312e-05,
|
|
"loss": 0.7032,
|
|
"step": 200
|
|
},
|
|
{
|
|
"epoch": 0.17761989342806395,
|
|
"grad_norm": 62910.03515625,
|
|
"learning_rate": 4.111900532859681e-05,
|
|
"loss": 0.712,
|
|
"step": 300
|
|
},
|
|
{
|
|
"epoch": 0.23682652457075193,
|
|
"grad_norm": 60269.59765625,
|
|
"learning_rate": 3.8158673771462406e-05,
|
|
"loss": 0.6845,
|
|
"step": 400
|
|
},
|
|
{
|
|
"epoch": 0.2960331557134399,
|
|
"grad_norm": 48000.21875,
|
|
"learning_rate": 3.5198342214328006e-05,
|
|
"loss": 0.6896,
|
|
"step": 500
|
|
},
|
|
{
|
|
"epoch": 0.3552397868561279,
|
|
"grad_norm": 69728.296875,
|
|
"learning_rate": 3.2238010657193605e-05,
|
|
"loss": 0.6967,
|
|
"step": 600
|
|
},
|
|
{
|
|
"epoch": 0.4144464179988159,
|
|
"grad_norm": 58644.7578125,
|
|
"learning_rate": 2.9277679100059208e-05,
|
|
"loss": 0.6894,
|
|
"step": 700
|
|
},
|
|
{
|
|
"epoch": 0.47365304914150386,
|
|
"grad_norm": 58962.94921875,
|
|
"learning_rate": 2.6317347542924807e-05,
|
|
"loss": 0.6831,
|
|
"step": 800
|
|
},
|
|
{
|
|
"epoch": 0.5328596802841918,
|
|
"grad_norm": 59192.22265625,
|
|
"learning_rate": 2.335701598579041e-05,
|
|
"loss": 0.6745,
|
|
"step": 900
|
|
},
|
|
{
|
|
"epoch": 0.5920663114268798,
|
|
"grad_norm": 58689.921875,
|
|
"learning_rate": 2.039668442865601e-05,
|
|
"loss": 0.6616,
|
|
"step": 1000
|
|
},
|
|
{
|
|
"epoch": 0.6512729425695678,
|
|
"grad_norm": 51845.45703125,
|
|
"learning_rate": 1.743635287152161e-05,
|
|
"loss": 0.6563,
|
|
"step": 1100
|
|
},
|
|
{
|
|
"epoch": 0.7104795737122558,
|
|
"grad_norm": 55519.21484375,
|
|
"learning_rate": 1.4476021314387211e-05,
|
|
"loss": 0.6345,
|
|
"step": 1200
|
|
},
|
|
{
|
|
"epoch": 0.7696862048549438,
|
|
"grad_norm": 60519.421875,
|
|
"learning_rate": 1.1515689757252812e-05,
|
|
"loss": 0.6346,
|
|
"step": 1300
|
|
},
|
|
{
|
|
"epoch": 0.8288928359976317,
|
|
"grad_norm": 59432.31640625,
|
|
"learning_rate": 8.555358200118415e-06,
|
|
"loss": 0.6711,
|
|
"step": 1400
|
|
},
|
|
{
|
|
"epoch": 0.8880994671403197,
|
|
"grad_norm": 58101.1015625,
|
|
"learning_rate": 5.595026642984015e-06,
|
|
"loss": 0.6353,
|
|
"step": 1500
|
|
},
|
|
{
|
|
"epoch": 0.9473060982830077,
|
|
"grad_norm": 62020.96875,
|
|
"learning_rate": 2.634695085849615e-06,
|
|
"loss": 0.6437,
|
|
"step": 1600
|
|
},
|
|
{
|
|
"epoch": 1.0,
|
|
"step": 1689,
|
|
"total_flos": 2.5754690641723392e+17,
|
|
"train_loss": 0.6758780561303726,
|
|
"train_runtime": 23583.4151,
|
|
"train_samples_per_second": 0.859,
|
|
"train_steps_per_second": 0.072
|
|
}
|
|
],
|
|
"logging_steps": 100,
|
|
"max_steps": 1689,
|
|
"num_input_tokens_seen": 0,
|
|
"num_train_epochs": 1,
|
|
"save_steps": 1689,
|
|
"stateful_callbacks": {
|
|
"TrainerControl": {
|
|
"args": {
|
|
"should_epoch_stop": false,
|
|
"should_evaluate": false,
|
|
"should_log": false,
|
|
"should_save": true,
|
|
"should_training_stop": true
|
|
},
|
|
"attributes": {}
|
|
}
|
|
},
|
|
"total_flos": 2.5754690641723392e+17,
|
|
"train_batch_size": 12,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|