Leooyii/NTK_64k_Slimpajama_1B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Leooyii/NTK_64k_Slimpajama_1B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-12 15:17:01 +08:00
commit 6137df146f
13 changed files with 94246 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

388
trainer_state.json Normal file
View File

@@ -0,0 +1,388 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.997920997920998,
"eval_steps": 500,
"global_step": 60,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 0.0,
"loss": 5.4047,
"step": 1
},
{
"epoch": 0.03,
"learning_rate": 4.6275642631951835e-06,
"loss": 4.4142,
"step": 2
},
{
"epoch": 0.05,
"learning_rate": 7.3345158268416935e-06,
"loss": 4.5149,
"step": 3
},
{
"epoch": 0.07,
"learning_rate": 9.255128526390367e-06,
"loss": 3.7716,
"step": 4
},
{
"epoch": 0.08,
"learning_rate": 1.0744871473609633e-05,
"loss": 3.3638,
"step": 5
},
{
"epoch": 0.1,
"learning_rate": 1.1962080090036879e-05,
"loss": 2.7725,
"step": 6
},
{
"epoch": 0.12,
"learning_rate": 1.299121531141887e-05,
"loss": 2.5599,
"step": 7
},
{
"epoch": 0.13,
"learning_rate": 1.388269278958555e-05,
"loss": 2.4306,
"step": 8
},
{
"epoch": 0.15,
"learning_rate": 1.4669031653683387e-05,
"loss": 2.1624,
"step": 9
},
{
"epoch": 0.17,
"learning_rate": 1.537243573680482e-05,
"loss": 2.0444,
"step": 10
},
{
"epoch": 0.18,
"learning_rate": 1.600874212937343e-05,
"loss": 1.9676,
"step": 11
},
{
"epoch": 0.2,
"learning_rate": 1.6589644353232063e-05,
"loss": 1.8458,
"step": 12
},
{
"epoch": 0.22,
"learning_rate": 1.712402259777778e-05,
"loss": 1.8314,
"step": 13
},
{
"epoch": 0.23,
"learning_rate": 1.7618779574614054e-05,
"loss": 1.8304,
"step": 14
},
{
"epoch": 0.25,
"learning_rate": 1.8079387300451327e-05,
"loss": 1.7738,
"step": 15
},
{
"epoch": 0.27,
"learning_rate": 1.8510257052780734e-05,
"loss": 1.7805,
"step": 16
},
{
"epoch": 0.28,
"learning_rate": 1.891499697130832e-05,
"loss": 1.751,
"step": 17
},
{
"epoch": 0.3,
"learning_rate": 1.929659591687857e-05,
"loss": 1.6917,
"step": 18
},
{
"epoch": 0.32,
"learning_rate": 1.9657557553855117e-05,
"loss": 1.7093,
"step": 19
},
{
"epoch": 0.33,
"learning_rate": 2e-05,
"loss": 1.7375,
"step": 20
},
{
"epoch": 0.35,
"learning_rate": 2e-05,
"loss": 1.6819,
"step": 21
},
{
"epoch": 0.37,
"learning_rate": 1.95e-05,
"loss": 1.709,
"step": 22
},
{
"epoch": 0.38,
"learning_rate": 1.9e-05,
"loss": 1.6692,
"step": 23
},
{
"epoch": 0.4,
"learning_rate": 1.8500000000000002e-05,
"loss": 1.7028,
"step": 24
},
{
"epoch": 0.42,
"learning_rate": 1.8e-05,
"loss": 1.7053,
"step": 25
},
{
"epoch": 0.43,
"learning_rate": 1.7500000000000002e-05,
"loss": 1.6622,
"step": 26
},
{
"epoch": 0.45,
"learning_rate": 1.7e-05,
"loss": 1.6586,
"step": 27
},
{
"epoch": 0.47,
"learning_rate": 1.65e-05,
"loss": 1.6884,
"step": 28
},
{
"epoch": 0.48,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.6559,
"step": 29
},
{
"epoch": 0.5,
"learning_rate": 1.55e-05,
"loss": 1.6173,
"step": 30
},
{
"epoch": 0.52,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.6468,
"step": 31
},
{
"epoch": 0.53,
"learning_rate": 1.45e-05,
"loss": 1.6495,
"step": 32
},
{
"epoch": 0.55,
"learning_rate": 1.4e-05,
"loss": 1.6518,
"step": 33
},
{
"epoch": 0.57,
"learning_rate": 1.3500000000000001e-05,
"loss": 1.638,
"step": 34
},
{
"epoch": 0.58,
"learning_rate": 1.3000000000000001e-05,
"loss": 1.6725,
"step": 35
},
{
"epoch": 0.6,
"learning_rate": 1.25e-05,
"loss": 1.6123,
"step": 36
},
{
"epoch": 0.62,
"learning_rate": 1.2e-05,
"loss": 1.6365,
"step": 37
},
{
"epoch": 0.63,
"learning_rate": 1.15e-05,
"loss": 1.6473,
"step": 38
},
{
"epoch": 0.65,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.5988,
"step": 39
},
{
"epoch": 0.67,
"learning_rate": 1.0500000000000001e-05,
"loss": 1.6443,
"step": 40
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.6344,
"step": 41
},
{
"epoch": 0.7,
"learning_rate": 9.5e-06,
"loss": 1.6198,
"step": 42
},
{
"epoch": 0.72,
"learning_rate": 9e-06,
"loss": 1.6138,
"step": 43
},
{
"epoch": 0.73,
"learning_rate": 8.5e-06,
"loss": 1.6499,
"step": 44
},
{
"epoch": 0.75,
"learning_rate": 8.000000000000001e-06,
"loss": 1.6466,
"step": 45
},
{
"epoch": 0.77,
"learning_rate": 7.500000000000001e-06,
"loss": 1.6387,
"step": 46
},
{
"epoch": 0.78,
"learning_rate": 7e-06,
"loss": 1.6208,
"step": 47
},
{
"epoch": 0.8,
"learning_rate": 6.5000000000000004e-06,
"loss": 1.647,
"step": 48
},
{
"epoch": 0.81,
"learning_rate": 6e-06,
"loss": 1.6273,
"step": 49
},
{
"epoch": 0.83,
"learning_rate": 5.500000000000001e-06,
"loss": 1.6275,
"step": 50
},
{
"epoch": 0.85,
"learning_rate": 5e-06,
"loss": 1.598,
"step": 51
},
{
"epoch": 0.86,
"learning_rate": 4.5e-06,
"loss": 1.63,
"step": 52
},
{
"epoch": 0.88,
"learning_rate": 4.000000000000001e-06,
"loss": 1.6693,
"step": 53
},
{
"epoch": 0.9,
"learning_rate": 3.5e-06,
"loss": 1.6366,
"step": 54
},
{
"epoch": 0.91,
"learning_rate": 3e-06,
"loss": 1.5802,
"step": 55
},
{
"epoch": 0.93,
"learning_rate": 2.5e-06,
"loss": 1.6816,
"step": 56
},
{
"epoch": 0.95,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.6158,
"step": 57
},
{
"epoch": 0.96,
"learning_rate": 1.5e-06,
"loss": 1.6564,
"step": 58
},
{
"epoch": 0.98,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.6194,
"step": 59
},
{
"epoch": 1.0,
"learning_rate": 5.000000000000001e-07,
"loss": 1.6099,
"step": 60
},
{
"epoch": 1.0,
"step": 60,
"total_flos": 1607198236999680.0,
"train_loss": 1.9521601617336273,
"train_runtime": 86972.6725,
"train_samples_per_second": 0.177,
"train_steps_per_second": 0.001
}
],
"logging_steps": 1.0,
"max_steps": 60,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 1607198236999680.0,
"trial_name": null,
"trial_params": null
}