Your Name
245 lines
5.2 KiB
JSON
245 lines
5.2 KiB
JSON
{
|
|
"best_global_step": null,
|
|
"best_metric": null,
|
|
"best_model_checkpoint": null,
|
|
"epoch": 0.012,
|
|
"eval_steps": 500,
|
|
"global_step": 30,
|
|
"is_hyper_param_search": false,
|
|
"is_local_process_zero": true,
|
|
"is_world_process_zero": true,
|
|
"log_history": [
|
|
{
|
|
"epoch": 0.0004,
|
|
"grad_norm": 0.21889594197273254,
|
|
"learning_rate": 0.0,
|
|
"loss": 1.3922,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.0008,
|
|
"grad_norm": 0.281279057264328,
|
|
"learning_rate": 4e-05,
|
|
"loss": 1.4108,
|
|
"step": 2
|
|
},
|
|
{
|
|
"epoch": 0.0012,
|
|
"grad_norm": 0.3023129999637604,
|
|
"learning_rate": 8e-05,
|
|
"loss": 1.3522,
|
|
"step": 3
|
|
},
|
|
{
|
|
"epoch": 0.0016,
|
|
"grad_norm": 0.2667141556739807,
|
|
"learning_rate": 0.00012,
|
|
"loss": 1.3634,
|
|
"step": 4
|
|
},
|
|
{
|
|
"epoch": 0.002,
|
|
"grad_norm": 0.25083309412002563,
|
|
"learning_rate": 0.00016,
|
|
"loss": 1.3984,
|
|
"step": 5
|
|
},
|
|
{
|
|
"epoch": 0.0024,
|
|
"grad_norm": 0.24728843569755554,
|
|
"learning_rate": 0.0002,
|
|
"loss": 1.2984,
|
|
"step": 6
|
|
},
|
|
{
|
|
"epoch": 0.0028,
|
|
"grad_norm": 0.19864429533481598,
|
|
"learning_rate": 0.000192,
|
|
"loss": 1.2225,
|
|
"step": 7
|
|
},
|
|
{
|
|
"epoch": 0.0032,
|
|
"grad_norm": 0.20911765098571777,
|
|
"learning_rate": 0.00018400000000000003,
|
|
"loss": 1.1594,
|
|
"step": 8
|
|
},
|
|
{
|
|
"epoch": 0.0036,
|
|
"grad_norm": 0.3918673098087311,
|
|
"learning_rate": 0.00017600000000000002,
|
|
"loss": 1.0998,
|
|
"step": 9
|
|
},
|
|
{
|
|
"epoch": 0.004,
|
|
"grad_norm": 0.2317754626274109,
|
|
"learning_rate": 0.000168,
|
|
"loss": 1.0553,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.0044,
|
|
"grad_norm": 0.2284780591726303,
|
|
"learning_rate": 0.00016,
|
|
"loss": 1.0439,
|
|
"step": 11
|
|
},
|
|
{
|
|
"epoch": 0.0048,
|
|
"grad_norm": 0.23215815424919128,
|
|
"learning_rate": 0.000152,
|
|
"loss": 0.9784,
|
|
"step": 12
|
|
},
|
|
{
|
|
"epoch": 0.0052,
|
|
"grad_norm": 0.24038466811180115,
|
|
"learning_rate": 0.000144,
|
|
"loss": 1.0631,
|
|
"step": 13
|
|
},
|
|
{
|
|
"epoch": 0.0056,
|
|
"grad_norm": 0.3637539744377136,
|
|
"learning_rate": 0.00013600000000000003,
|
|
"loss": 1.062,
|
|
"step": 14
|
|
},
|
|
{
|
|
"epoch": 0.006,
|
|
"grad_norm": 0.2320483773946762,
|
|
"learning_rate": 0.00012800000000000002,
|
|
"loss": 1.0589,
|
|
"step": 15
|
|
},
|
|
{
|
|
"epoch": 0.0064,
|
|
"grad_norm": 0.22827845811843872,
|
|
"learning_rate": 0.00012,
|
|
"loss": 1.0331,
|
|
"step": 16
|
|
},
|
|
{
|
|
"epoch": 0.0068,
|
|
"grad_norm": 0.22989106178283691,
|
|
"learning_rate": 0.00011200000000000001,
|
|
"loss": 1.024,
|
|
"step": 17
|
|
},
|
|
{
|
|
"epoch": 0.0072,
|
|
"grad_norm": 0.2284201979637146,
|
|
"learning_rate": 0.00010400000000000001,
|
|
"loss": 1.0054,
|
|
"step": 18
|
|
},
|
|
{
|
|
"epoch": 0.0076,
|
|
"grad_norm": 0.23722527921199799,
|
|
"learning_rate": 9.6e-05,
|
|
"loss": 1.0607,
|
|
"step": 19
|
|
},
|
|
{
|
|
"epoch": 0.008,
|
|
"grad_norm": 0.25204116106033325,
|
|
"learning_rate": 8.800000000000001e-05,
|
|
"loss": 1.1038,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.0084,
|
|
"grad_norm": 0.23097504675388336,
|
|
"learning_rate": 8e-05,
|
|
"loss": 0.9563,
|
|
"step": 21
|
|
},
|
|
{
|
|
"epoch": 0.0088,
|
|
"grad_norm": 0.21278901398181915,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 0.9815,
|
|
"step": 22
|
|
},
|
|
{
|
|
"epoch": 0.0092,
|
|
"grad_norm": 0.3004467785358429,
|
|
"learning_rate": 6.400000000000001e-05,
|
|
"loss": 0.9571,
|
|
"step": 23
|
|
},
|
|
{
|
|
"epoch": 0.0096,
|
|
"grad_norm": 0.24711133539676666,
|
|
"learning_rate": 5.6000000000000006e-05,
|
|
"loss": 1.0638,
|
|
"step": 24
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"grad_norm": 0.2166084498167038,
|
|
"learning_rate": 4.8e-05,
|
|
"loss": 1.0215,
|
|
"step": 25
|
|
},
|
|
{
|
|
"epoch": 0.0104,
|
|
"grad_norm": 0.21120785176753998,
|
|
"learning_rate": 4e-05,
|
|
"loss": 0.9826,
|
|
"step": 26
|
|
},
|
|
{
|
|
"epoch": 0.0108,
|
|
"grad_norm": 0.19642344117164612,
|
|
"learning_rate": 3.2000000000000005e-05,
|
|
"loss": 0.9539,
|
|
"step": 27
|
|
},
|
|
{
|
|
"epoch": 0.0112,
|
|
"grad_norm": 0.2176462709903717,
|
|
"learning_rate": 2.4e-05,
|
|
"loss": 0.884,
|
|
"step": 28
|
|
},
|
|
{
|
|
"epoch": 0.0116,
|
|
"grad_norm": 0.20913571119308472,
|
|
"learning_rate": 1.6000000000000003e-05,
|
|
"loss": 0.9816,
|
|
"step": 29
|
|
},
|
|
{
|
|
"epoch": 0.012,
|
|
"grad_norm": 0.1878669112920761,
|
|
"learning_rate": 8.000000000000001e-06,
|
|
"loss": 0.9465,
|
|
"step": 30
|
|
}
|
|
],
|
|
"logging_steps": 1,
|
|
"max_steps": 30,
|
|
"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": 8.665233697510195e+16,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|