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": 0.14046324789524078,
|
|
"learning_rate": 0.0,
|
|
"loss": 1.3922,
|
|
"step": 1
|
|
},
|
|
{
|
|
"epoch": 0.0008,
|
|
"grad_norm": 0.17429180443286896,
|
|
"learning_rate": 4e-05,
|
|
"loss": 1.4108,
|
|
"step": 2
|
|
},
|
|
{
|
|
"epoch": 0.0012,
|
|
"grad_norm": 0.18312247097492218,
|
|
"learning_rate": 8e-05,
|
|
"loss": 1.3525,
|
|
"step": 3
|
|
},
|
|
{
|
|
"epoch": 0.0016,
|
|
"grad_norm": 0.2110716551542282,
|
|
"learning_rate": 0.00012,
|
|
"loss": 1.3662,
|
|
"step": 4
|
|
},
|
|
{
|
|
"epoch": 0.002,
|
|
"grad_norm": 0.1712651401758194,
|
|
"learning_rate": 0.00016,
|
|
"loss": 1.4026,
|
|
"step": 5
|
|
},
|
|
{
|
|
"epoch": 0.0024,
|
|
"grad_norm": 0.1721387505531311,
|
|
"learning_rate": 0.0002,
|
|
"loss": 1.3036,
|
|
"step": 6
|
|
},
|
|
{
|
|
"epoch": 0.0028,
|
|
"grad_norm": 0.146767720580101,
|
|
"learning_rate": 0.000192,
|
|
"loss": 1.2262,
|
|
"step": 7
|
|
},
|
|
{
|
|
"epoch": 0.0032,
|
|
"grad_norm": 0.1462695449590683,
|
|
"learning_rate": 0.00018400000000000003,
|
|
"loss": 1.1611,
|
|
"step": 8
|
|
},
|
|
{
|
|
"epoch": 0.0036,
|
|
"grad_norm": 0.22634515166282654,
|
|
"learning_rate": 0.00017600000000000002,
|
|
"loss": 1.1031,
|
|
"step": 9
|
|
},
|
|
{
|
|
"epoch": 0.004,
|
|
"grad_norm": 0.16959479451179504,
|
|
"learning_rate": 0.000168,
|
|
"loss": 1.0576,
|
|
"step": 10
|
|
},
|
|
{
|
|
"epoch": 0.0044,
|
|
"grad_norm": 0.15298032760620117,
|
|
"learning_rate": 0.00016,
|
|
"loss": 1.0452,
|
|
"step": 11
|
|
},
|
|
{
|
|
"epoch": 0.0048,
|
|
"grad_norm": 0.1880827248096466,
|
|
"learning_rate": 0.000152,
|
|
"loss": 0.9791,
|
|
"step": 12
|
|
},
|
|
{
|
|
"epoch": 0.0052,
|
|
"grad_norm": 0.16587546467781067,
|
|
"learning_rate": 0.000144,
|
|
"loss": 1.0639,
|
|
"step": 13
|
|
},
|
|
{
|
|
"epoch": 0.0056,
|
|
"grad_norm": 0.1673472821712494,
|
|
"learning_rate": 0.00013600000000000003,
|
|
"loss": 1.0612,
|
|
"step": 14
|
|
},
|
|
{
|
|
"epoch": 0.006,
|
|
"grad_norm": 0.1644534170627594,
|
|
"learning_rate": 0.00012800000000000002,
|
|
"loss": 1.0584,
|
|
"step": 15
|
|
},
|
|
{
|
|
"epoch": 0.0064,
|
|
"grad_norm": 0.168317511677742,
|
|
"learning_rate": 0.00012,
|
|
"loss": 1.0348,
|
|
"step": 16
|
|
},
|
|
{
|
|
"epoch": 0.0068,
|
|
"grad_norm": 0.2933410704135895,
|
|
"learning_rate": 0.00011200000000000001,
|
|
"loss": 1.0254,
|
|
"step": 17
|
|
},
|
|
{
|
|
"epoch": 0.0072,
|
|
"grad_norm": 0.16315768659114838,
|
|
"learning_rate": 0.00010400000000000001,
|
|
"loss": 1.0078,
|
|
"step": 18
|
|
},
|
|
{
|
|
"epoch": 0.0076,
|
|
"grad_norm": 0.17154046893119812,
|
|
"learning_rate": 9.6e-05,
|
|
"loss": 1.0626,
|
|
"step": 19
|
|
},
|
|
{
|
|
"epoch": 0.008,
|
|
"grad_norm": 0.2063586413860321,
|
|
"learning_rate": 8.800000000000001e-05,
|
|
"loss": 1.1072,
|
|
"step": 20
|
|
},
|
|
{
|
|
"epoch": 0.0084,
|
|
"grad_norm": 0.1720573604106903,
|
|
"learning_rate": 8e-05,
|
|
"loss": 0.9562,
|
|
"step": 21
|
|
},
|
|
{
|
|
"epoch": 0.0088,
|
|
"grad_norm": 0.15085603296756744,
|
|
"learning_rate": 7.2e-05,
|
|
"loss": 0.9819,
|
|
"step": 22
|
|
},
|
|
{
|
|
"epoch": 0.0092,
|
|
"grad_norm": 0.16576017439365387,
|
|
"learning_rate": 6.400000000000001e-05,
|
|
"loss": 0.9569,
|
|
"step": 23
|
|
},
|
|
{
|
|
"epoch": 0.0096,
|
|
"grad_norm": 0.15237872302532196,
|
|
"learning_rate": 5.6000000000000006e-05,
|
|
"loss": 1.0633,
|
|
"step": 24
|
|
},
|
|
{
|
|
"epoch": 0.01,
|
|
"grad_norm": 0.16275323927402496,
|
|
"learning_rate": 4.8e-05,
|
|
"loss": 1.0202,
|
|
"step": 25
|
|
},
|
|
{
|
|
"epoch": 0.0104,
|
|
"grad_norm": 0.1494642049074173,
|
|
"learning_rate": 4e-05,
|
|
"loss": 0.9842,
|
|
"step": 26
|
|
},
|
|
{
|
|
"epoch": 0.0108,
|
|
"grad_norm": 0.14561104774475098,
|
|
"learning_rate": 3.2000000000000005e-05,
|
|
"loss": 0.9534,
|
|
"step": 27
|
|
},
|
|
{
|
|
"epoch": 0.0112,
|
|
"grad_norm": 0.1298287808895111,
|
|
"learning_rate": 2.4e-05,
|
|
"loss": 0.8834,
|
|
"step": 28
|
|
},
|
|
{
|
|
"epoch": 0.0116,
|
|
"grad_norm": 0.15824304521083832,
|
|
"learning_rate": 1.6000000000000003e-05,
|
|
"loss": 0.9824,
|
|
"step": 29
|
|
},
|
|
{
|
|
"epoch": 0.012,
|
|
"grad_norm": 0.1302255243062973,
|
|
"learning_rate": 8.000000000000001e-06,
|
|
"loss": 0.9466,
|
|
"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": 8.690976238834483e+16,
|
|
"train_batch_size": 1,
|
|
"trial_name": null,
|
|
"trial_params": null
|
|
}
|