fpadovani/tur_indomain_prepretraining_seed577
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: fpadovani/tur_indomain_prepretraining_seed577
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-30 04:36:21 +08:00
commit 7dbe71f216
97 changed files with 2033223 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
checkpoint-500/config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"_name_or_path": "goldfish-models/tur_latn_10mb",
"activation_function": "gelu",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50000,
"embd_pdrop": 0.1,
"eos_token_id": 50001,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 2048,
"n_embd": 512,
"n_head": 8,
"n_inner": 2048,
"n_layer": 4,
"n_positions": 2048,
"pad_token_id": 50002,
"prefix": "[CLS]",
"reorder_and_upcast_attn": false,
"resid_pdrop": 0.1,
"scale_attn_by_inverse_layer_idx": false,
"scale_attn_weights": true,
"summary_activation": null,
"summary_first_dropout": 0.1,
"summary_proj_to_labels": true,
"summary_type": "cls_index",
"summary_use_proj": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.47.0",
"use_cache": true,
"vocab_size": 51200
}

7
checkpoint-500/generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 50000,
"eos_token_id": 50001,
"pad_token_id": 50002,
"transformers_version": "4.47.0"
}

3
checkpoint-500/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7c9e376ce556a5336310da4308b7abbf5a49d021629da77f8eebad222b6761b1
size 79752272

3
checkpoint-500/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c67791844b3ab1e1c118a1440d1be978538e6063429cf1062c9850223bf80bb3
size 159538443

3
checkpoint-500/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:678c42a1f81ca322dd86dd40209eda932f87e51895fd1824b1d43ced2a361ea4
size 14645

3
checkpoint-500/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f243d020d2631ea115c3f5d3e6c1e5c9a7f8334b45c5f10056444d8c3da615c
size 1465

1249
checkpoint-500/special_tokens_map.json Normal file
View File

File diff suppressed because it is too large Load Diff

210940
checkpoint-500/tokenizer.json Normal file
View File

File diff suppressed because one or more lines are too long

10829
checkpoint-500/tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

733
checkpoint-500/trainer_state.json Normal file
View File

@@ -0,0 +1,733 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0653893938403191,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.000653893938403191,
"grad_norm": 7.78125,
"learning_rate": 1e-05,
"loss": 10.9314,
"step": 5
},
{
"epoch": 0.001307787876806382,
"grad_norm": 7.15625,
"learning_rate": 2e-05,
"loss": 10.8618,
"step": 10
},
{
"epoch": 0.001961681815209573,
"grad_norm": 8.625,
"learning_rate": 3e-05,
"loss": 10.6602,
"step": 15
},
{
"epoch": 0.002615575753612764,
"grad_norm": 3.78125,
"learning_rate": 4e-05,
"loss": 10.4672,
"step": 20
},
{
"epoch": 0.003269469692015955,
"grad_norm": 3.21875,
"learning_rate": 5e-05,
"loss": 10.3043,
"step": 25
},
{
"epoch": 0.003923363630419146,
"grad_norm": 2.921875,
"learning_rate": 6e-05,
"loss": 10.2382,
"step": 30
},
{
"epoch": 0.004577257568822337,
"grad_norm": 2.84375,
"learning_rate": 7.000000000000001e-05,
"loss": 10.072,
"step": 35
},
{
"epoch": 0.005231151507225528,
"grad_norm": 2.84375,
"learning_rate": 8e-05,
"loss": 9.9208,
"step": 40
},
{
"epoch": 0.005885045445628719,
"grad_norm": 2.5,
"learning_rate": 8.999999999999999e-05,
"loss": 9.7828,
"step": 45
},
{
"epoch": 0.00653893938403191,
"grad_norm": 2.53125,
"learning_rate": 0.0001,
"loss": 9.5983,
"step": 50
},
{
"epoch": 0.007192833322435101,
"grad_norm": 2.515625,
"learning_rate": 0.00011,
"loss": 9.3536,
"step": 55
},
{
"epoch": 0.007846727260838291,
"grad_norm": 2.265625,
"learning_rate": 0.00012,
"loss": 9.1994,
"step": 60
},
{
"epoch": 0.008500621199241483,
"grad_norm": 1.96875,
"learning_rate": 0.00013000000000000002,
"loss": 9.0285,
"step": 65
},
{
"epoch": 0.009154515137644674,
"grad_norm": 1.734375,
"learning_rate": 0.00014000000000000001,
"loss": 8.8309,
"step": 70
},
{
"epoch": 0.009808409076047865,
"grad_norm": 1.6484375,
"learning_rate": 0.00015,
"loss": 8.7217,
"step": 75
},
{
"epoch": 0.010462303014451056,
"grad_norm": 1.296875,
"learning_rate": 0.00016,
"loss": 8.5904,
"step": 80
},
{
"epoch": 0.011116196952854247,
"grad_norm": 1.140625,
"learning_rate": 0.00017,
"loss": 8.5347,
"step": 85
},
{
"epoch": 0.011770090891257438,
"grad_norm": 1.1484375,
"learning_rate": 0.00017999999999999998,
"loss": 8.5,
"step": 90
},
{
"epoch": 0.01242398482966063,
"grad_norm": 1.265625,
"learning_rate": 0.00019,
"loss": 8.4191,
"step": 95
},
{
"epoch": 0.01307787876806382,
"grad_norm": 1.296875,
"learning_rate": 0.0002,
"loss": 8.4152,
"step": 100
},
{
"epoch": 0.013731772706467011,
"grad_norm": 1.25,
"learning_rate": 0.00021,
"loss": 8.4117,
"step": 105
},
{
"epoch": 0.014385666644870202,
"grad_norm": 1.3984375,
"learning_rate": 0.00022,
"loss": 8.3862,
"step": 110
},
{
"epoch": 0.015039560583273394,
"grad_norm": 1.6484375,
"learning_rate": 0.00023,
"loss": 8.3845,
"step": 115
},
{
"epoch": 0.015693454521676583,
"grad_norm": 1.6015625,
"learning_rate": 0.00024,
"loss": 8.3856,
"step": 120
},
{
"epoch": 0.016347348460079774,
"grad_norm": 2.140625,
"learning_rate": 0.00025,
"loss": 8.3267,
"step": 125
},
{
"epoch": 0.017001242398482965,
"grad_norm": 1.5625,
"learning_rate": 0.00026000000000000003,
"loss": 8.3117,
"step": 130
},
{
"epoch": 0.017655136336886156,
"grad_norm": 1.46875,
"learning_rate": 0.00027,
"loss": 8.2819,
"step": 135
},
{
"epoch": 0.018309030275289347,
"grad_norm": 1.890625,
"learning_rate": 0.00028000000000000003,
"loss": 8.3206,
"step": 140
},
{
"epoch": 0.01896292421369254,
"grad_norm": 1.390625,
"learning_rate": 0.00029,
"loss": 8.2799,
"step": 145
},
{
"epoch": 0.01961681815209573,
"grad_norm": 1.609375,
"learning_rate": 0.0003,
"loss": 8.2797,
"step": 150
},
{
"epoch": 0.02027071209049892,
"grad_norm": 1.65625,
"learning_rate": 0.00031,
"loss": 8.2185,
"step": 155
},
{
"epoch": 0.02092460602890211,
"grad_norm": 1.734375,
"learning_rate": 0.00032,
"loss": 8.1803,
"step": 160
},
{
"epoch": 0.021578499967305303,
"grad_norm": 2.109375,
"learning_rate": 0.00033,
"loss": 8.1965,
"step": 165
},
{
"epoch": 0.022232393905708494,
"grad_norm": 1.3984375,
"learning_rate": 0.00034,
"loss": 8.1966,
"step": 170
},
{
"epoch": 0.022886287844111685,
"grad_norm": 2.3125,
"learning_rate": 0.00035,
"loss": 8.1858,
"step": 175
},
{
"epoch": 0.023540181782514876,
"grad_norm": 1.8359375,
"learning_rate": 0.00035999999999999997,
"loss": 8.1155,
"step": 180
},
{
"epoch": 0.024194075720918067,
"grad_norm": 1.703125,
"learning_rate": 0.00037,
"loss": 8.0795,
"step": 185
},
{
"epoch": 0.02484796965932126,
"grad_norm": 1.6953125,
"learning_rate": 0.00038,
"loss": 8.0587,
"step": 190
},
{
"epoch": 0.02550186359772445,
"grad_norm": 1.4453125,
"learning_rate": 0.00039000000000000005,
"loss": 8.0238,
"step": 195
},
{
"epoch": 0.02615575753612764,
"grad_norm": 1.421875,
"learning_rate": 0.0004,
"loss": 8.0203,
"step": 200
},
{
"epoch": 0.02680965147453083,
"grad_norm": 1.65625,
"learning_rate": 0.00041,
"loss": 8.0557,
"step": 205
},
{
"epoch": 0.027463545412934023,
"grad_norm": 1.5546875,
"learning_rate": 0.00042,
"loss": 8.0153,
"step": 210
},
{
"epoch": 0.028117439351337214,
"grad_norm": 1.4453125,
"learning_rate": 0.00043,
"loss": 8.0324,
"step": 215
},
{
"epoch": 0.028771333289740405,
"grad_norm": 1.6640625,
"learning_rate": 0.00044,
"loss": 7.943,
"step": 220
},
{
"epoch": 0.029425227228143596,
"grad_norm": 1.765625,
"learning_rate": 0.00045000000000000004,
"loss": 7.9174,
"step": 225
},
{
"epoch": 0.030079121166546787,
"grad_norm": 1.484375,
"learning_rate": 0.00046,
"loss": 7.9345,
"step": 230
},
{
"epoch": 0.030733015104949978,
"grad_norm": 1.625,
"learning_rate": 0.00047,
"loss": 7.8904,
"step": 235
},
{
"epoch": 0.031386909043353166,
"grad_norm": 1.6015625,
"learning_rate": 0.00048,
"loss": 7.9578,
"step": 240
},
{
"epoch": 0.03204080298175636,
"grad_norm": 1.6328125,
"learning_rate": 0.00049,
"loss": 7.8584,
"step": 245
},
{
"epoch": 0.03269469692015955,
"grad_norm": 1.953125,
"learning_rate": 0.0005,
"loss": 7.8777,
"step": 250
},
{
"epoch": 0.03334859085856274,
"grad_norm": 1.5234375,
"learning_rate": 0.00051,
"loss": 7.8879,
"step": 255
},
{
"epoch": 0.03400248479696593,
"grad_norm": 1.5859375,
"learning_rate": 0.0005200000000000001,
"loss": 7.8749,
"step": 260
},
{
"epoch": 0.03465637873536912,
"grad_norm": 1.5078125,
"learning_rate": 0.0005300000000000001,
"loss": 7.8588,
"step": 265
},
{
"epoch": 0.03531027267377231,
"grad_norm": 1.8125,
"learning_rate": 0.00054,
"loss": 7.8164,
"step": 270
},
{
"epoch": 0.035964166612175504,
"grad_norm": 1.890625,
"learning_rate": 0.00055,
"loss": 7.8153,
"step": 275
},
{
"epoch": 0.036618060550578695,
"grad_norm": 1.828125,
"learning_rate": 0.0005600000000000001,
"loss": 7.8396,
"step": 280
},
{
"epoch": 0.037271954488981886,
"grad_norm": 1.6171875,
"learning_rate": 0.00057,
"loss": 7.8175,
"step": 285
},
{
"epoch": 0.03792584842738508,
"grad_norm": 1.609375,
"learning_rate": 0.00058,
"loss": 7.8173,
"step": 290
},
{
"epoch": 0.03857974236578827,
"grad_norm": 1.765625,
"learning_rate": 0.00059,
"loss": 7.7171,
"step": 295
},
{
"epoch": 0.03923363630419146,
"grad_norm": 1.46875,
"learning_rate": 0.0006,
"loss": 7.7434,
"step": 300
},
{
"epoch": 0.03988753024259465,
"grad_norm": 1.75,
"learning_rate": 0.00061,
"loss": 7.7722,
"step": 305
},
{
"epoch": 0.04054142418099784,
"grad_norm": 1.5859375,
"learning_rate": 0.00062,
"loss": 7.7211,
"step": 310
},
{
"epoch": 0.04119531811940103,
"grad_norm": 1.390625,
"learning_rate": 0.00063,
"loss": 7.7748,
"step": 315
},
{
"epoch": 0.04184921205780422,
"grad_norm": 1.59375,
"learning_rate": 0.00064,
"loss": 7.6554,
"step": 320
},
{
"epoch": 0.042503105996207415,
"grad_norm": 1.5,
"learning_rate": 0.0006500000000000001,
"loss": 7.6331,
"step": 325
},
{
"epoch": 0.043156999934610606,
"grad_norm": 1.484375,
"learning_rate": 0.00066,
"loss": 7.7316,
"step": 330
},
{
"epoch": 0.0438108938730138,
"grad_norm": 1.65625,
"learning_rate": 0.00067,
"loss": 7.6819,
"step": 335
},
{
"epoch": 0.04446478781141699,
"grad_norm": 1.65625,
"learning_rate": 0.00068,
"loss": 7.6488,
"step": 340
},
{
"epoch": 0.04511868174982018,
"grad_norm": 1.4921875,
"learning_rate": 0.00069,
"loss": 7.5754,
"step": 345
},
{
"epoch": 0.04577257568822337,
"grad_norm": 1.4609375,
"learning_rate": 0.0007,
"loss": 7.6011,
"step": 350
},
{
"epoch": 0.04642646962662656,
"grad_norm": 1.703125,
"learning_rate": 0.00071,
"loss": 7.5742,
"step": 355
},
{
"epoch": 0.04708036356502975,
"grad_norm": 1.5,
"learning_rate": 0.0007199999999999999,
"loss": 7.5733,
"step": 360
},
{
"epoch": 0.04773425750343294,
"grad_norm": 1.390625,
"learning_rate": 0.00073,
"loss": 7.5406,
"step": 365
},
{
"epoch": 0.048388151441836134,
"grad_norm": 1.5390625,
"learning_rate": 0.00074,
"loss": 7.5902,
"step": 370
},
{
"epoch": 0.049042045380239326,
"grad_norm": 1.4296875,
"learning_rate": 0.00075,
"loss": 7.5615,
"step": 375
},
{
"epoch": 0.04969593931864252,
"grad_norm": 1.5625,
"learning_rate": 0.00076,
"loss": 7.5224,
"step": 380
},
{
"epoch": 0.05034983325704571,
"grad_norm": 1.546875,
"learning_rate": 0.0007700000000000001,
"loss": 7.5185,
"step": 385
},
{
"epoch": 0.0510037271954489,
"grad_norm": 1.65625,
"learning_rate": 0.0007800000000000001,
"loss": 7.4919,
"step": 390
},
{
"epoch": 0.05165762113385209,
"grad_norm": 1.59375,
"learning_rate": 0.00079,
"loss": 7.4876,
"step": 395
},
{
"epoch": 0.05231151507225528,
"grad_norm": 1.578125,
"learning_rate": 0.0008,
"loss": 7.4722,
"step": 400
},
{
"epoch": 0.05296540901065847,
"grad_norm": 1.6640625,
"learning_rate": 0.0008100000000000001,
"loss": 7.498,
"step": 405
},
{
"epoch": 0.05361930294906166,
"grad_norm": 1.5390625,
"learning_rate": 0.00082,
"loss": 7.4047,
"step": 410
},
{
"epoch": 0.054273196887464854,
"grad_norm": 1.5078125,
"learning_rate": 0.00083,
"loss": 7.4376,
"step": 415
},
{
"epoch": 0.054927090825868045,
"grad_norm": 1.734375,
"learning_rate": 0.00084,
"loss": 7.4518,
"step": 420
},
{
"epoch": 0.055580984764271237,
"grad_norm": 1.453125,
"learning_rate": 0.00085,
"loss": 7.4957,
"step": 425
},
{
"epoch": 0.05623487870267443,
"grad_norm": 1.4453125,
"learning_rate": 0.00086,
"loss": 7.4782,
"step": 430
},
{
"epoch": 0.05688877264107762,
"grad_norm": 1.4140625,
"learning_rate": 0.00087,
"loss": 7.4289,
"step": 435
},
{
"epoch": 0.05754266657948081,
"grad_norm": 3.09375,
"learning_rate": 0.00088,
"loss": 7.4412,
"step": 440
},
{
"epoch": 0.058196560517884,
"grad_norm": 1.625,
"learning_rate": 0.0008900000000000001,
"loss": 7.413,
"step": 445
},
{
"epoch": 0.05885045445628719,
"grad_norm": 1.5546875,
"learning_rate": 0.0009000000000000001,
"loss": 7.4372,
"step": 450
},
{
"epoch": 0.05950434839469038,
"grad_norm": 1.5546875,
"learning_rate": 0.00091,
"loss": 7.3155,
"step": 455
},
{
"epoch": 0.060158242333093574,
"grad_norm": 1.3828125,
"learning_rate": 0.00092,
"loss": 7.4253,
"step": 460
},
{
"epoch": 0.060812136271496765,
"grad_norm": 1.4296875,
"learning_rate": 0.00093,
"loss": 7.3755,
"step": 465
},
{
"epoch": 0.061466030209899956,
"grad_norm": 1.5546875,
"learning_rate": 0.00094,
"loss": 7.391,
"step": 470
},
{
"epoch": 0.06211992414830315,
"grad_norm": 1.5703125,
"learning_rate": 0.00095,
"loss": 7.3909,
"step": 475
},
{
"epoch": 0.06277381808670633,
"grad_norm": 1.5,
"learning_rate": 0.00096,
"loss": 7.3484,
"step": 480
},
{
"epoch": 0.06342771202510952,
"grad_norm": 1.609375,
"learning_rate": 0.0009699999999999999,
"loss": 7.3424,
"step": 485
},
{
"epoch": 0.06408160596351271,
"grad_norm": 1.6953125,
"learning_rate": 0.00098,
"loss": 7.3676,
"step": 490
},
{
"epoch": 0.0647354999019159,
"grad_norm": 1.53125,
"learning_rate": 0.00099,
"loss": 7.2811,
"step": 495
},
{
"epoch": 0.0653893938403191,
"grad_norm": 1.53125,
"learning_rate": 0.001,
"loss": 7.2938,
"step": 500
}
],
"logging_steps": 5,
"max_steps": 4000,
"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": false
},
"attributes": {}
}
},
"total_flos": 683343042969600.0,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}

3
checkpoint-500/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5d844e9bd7269e969751057307f9b24ce1dc61943d4ef008f2ddc415e2d7a0e8
size 6161