SNSFL/SNSFL-Public-Release
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: SNSFL/SNSFL-Public-Release
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-25 02:36:19 +08:00
commit f69f966d20
975 changed files with 591373 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
last-checkpoint/config.json Normal file
View File

@@ -0,0 +1,41 @@
{
"activation_function": "gelu_new",
"add_cross_attention": false,
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "gpt2",
"n_ctx": 1024,
"n_embd": 768,
"n_head": 12,
"n_inner": null,
"n_layer": 12,
"n_positions": 1024,
"pad_token_id": null,
"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,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"tie_word_embeddings": true,
"transformers_version": "5.0.0",
"use_cache": false,
"vocab_size": 50257
}

6
last-checkpoint/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "5.0.0"
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3934edb64849161e35e0081b9dd5f0e63a5e356396de30d09ae40df9d376df96
size 497774208

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8fc3bd04a20b8a6474a44e11cc658b42fb3380419258a2d168e9437d4e27008b
size 995644811

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a3ed03a6ce5d6899fce774b99e22e449c36d4c5119dd3c14d26c737c4f01c73b
size 14645

3
last-checkpoint/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf4cc1c3df50b8347d4881ead6e53bfb08e78f3ba2387afdc23119b640999563
size 1383

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e20399a05e9b6e319774eafa7c77de56e32cc297c6bc98934837edbe1ab8e66d
size 1465

250320
last-checkpoint/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

12
last-checkpoint/tokenizer_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": false,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

384
last-checkpoint/trainer_state.json Normal file
View File

@@ -0,0 +1,384 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.6042296072507553,
"eval_steps": 500,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.012084592145015106,
"grad_norm": 5.047657012939453,
"learning_rate": 5e-05,
"loss": 2.5133795738220215,
"step": 1
},
{
"epoch": 0.02416918429003021,
"grad_norm": Infinity,
"learning_rate": 4.9e-05,
"loss": 2.415961265563965,
"step": 2
},
{
"epoch": 0.03625377643504532,
"grad_norm": 6.5832695960998535,
"learning_rate": 4.8e-05,
"loss": 2.396810293197632,
"step": 3
},
{
"epoch": 0.04833836858006042,
"grad_norm": 4.395927906036377,
"learning_rate": 4.7e-05,
"loss": 2.2931461334228516,
"step": 4
},
{
"epoch": 0.06042296072507553,
"grad_norm": 4.7674384117126465,
"learning_rate": 4.600000000000001e-05,
"loss": 2.5129544734954834,
"step": 5
},
{
"epoch": 0.07250755287009064,
"grad_norm": 5.8445725440979,
"learning_rate": 4.5e-05,
"loss": 2.5405635833740234,
"step": 6
},
{
"epoch": 0.08459214501510574,
"grad_norm": 5.57906436920166,
"learning_rate": 4.4000000000000006e-05,
"loss": 2.346829891204834,
"step": 7
},
{
"epoch": 0.09667673716012085,
"grad_norm": 4.9558234214782715,
"learning_rate": 4.3e-05,
"loss": 2.509409189224243,
"step": 8
},
{
"epoch": 0.10876132930513595,
"grad_norm": 5.051382064819336,
"learning_rate": 4.2e-05,
"loss": 2.3653814792633057,
"step": 9
},
{
"epoch": 0.12084592145015106,
"grad_norm": 5.459464073181152,
"learning_rate": 4.1e-05,
"loss": 2.169222593307495,
"step": 10
},
{
"epoch": 0.13293051359516617,
"grad_norm": 4.501086235046387,
"learning_rate": 4e-05,
"loss": 2.0589377880096436,
"step": 11
},
{
"epoch": 0.14501510574018128,
"grad_norm": 5.01068115234375,
"learning_rate": 3.9000000000000006e-05,
"loss": 2.3503735065460205,
"step": 12
},
{
"epoch": 0.15709969788519637,
"grad_norm": 4.671829700469971,
"learning_rate": 3.8e-05,
"loss": 2.442352771759033,
"step": 13
},
{
"epoch": 0.1691842900302115,
"grad_norm": 5.119238376617432,
"learning_rate": 3.7e-05,
"loss": 2.558164596557617,
"step": 14
},
{
"epoch": 0.18126888217522658,
"grad_norm": 5.3008131980896,
"learning_rate": 3.6e-05,
"loss": 2.25809383392334,
"step": 15
},
{
"epoch": 0.1933534743202417,
"grad_norm": 5.134022235870361,
"learning_rate": 3.5e-05,
"loss": 2.3521411418914795,
"step": 16
},
{
"epoch": 0.2054380664652568,
"grad_norm": 5.3440680503845215,
"learning_rate": 3.4000000000000007e-05,
"loss": 2.2320029735565186,
"step": 17
},
{
"epoch": 0.2175226586102719,
"grad_norm": 5.0696611404418945,
"learning_rate": 3.3e-05,
"loss": 2.2702510356903076,
"step": 18
},
{
"epoch": 0.229607250755287,
"grad_norm": 4.738864898681641,
"learning_rate": 3.2000000000000005e-05,
"loss": 2.3271431922912598,
"step": 19
},
{
"epoch": 0.24169184290030213,
"grad_norm": 4.789466381072998,
"learning_rate": 3.1e-05,
"loss": 2.37686824798584,
"step": 20
},
{
"epoch": 0.2537764350453172,
"grad_norm": 4.57346248626709,
"learning_rate": 3e-05,
"loss": 2.2996890544891357,
"step": 21
},
{
"epoch": 0.26586102719033233,
"grad_norm": 5.35806941986084,
"learning_rate": 2.9e-05,
"loss": 2.2705211639404297,
"step": 22
},
{
"epoch": 0.27794561933534745,
"grad_norm": 5.366229057312012,
"learning_rate": 2.8000000000000003e-05,
"loss": 2.1707987785339355,
"step": 23
},
{
"epoch": 0.29003021148036257,
"grad_norm": 4.525028705596924,
"learning_rate": 2.7000000000000002e-05,
"loss": 2.21423602104187,
"step": 24
},
{
"epoch": 0.3021148036253776,
"grad_norm": 4.6029133796691895,
"learning_rate": 2.6000000000000002e-05,
"loss": 2.2529592514038086,
"step": 25
},
{
"epoch": 0.31419939577039274,
"grad_norm": 6.479076385498047,
"learning_rate": 2.5e-05,
"loss": 2.235084056854248,
"step": 26
},
{
"epoch": 0.32628398791540786,
"grad_norm": 4.90264892578125,
"learning_rate": 2.4e-05,
"loss": 2.4324228763580322,
"step": 27
},
{
"epoch": 0.338368580060423,
"grad_norm": 4.789745807647705,
"learning_rate": 2.3000000000000003e-05,
"loss": 2.3905863761901855,
"step": 28
},
{
"epoch": 0.3504531722054381,
"grad_norm": 4.345789909362793,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.219896078109741,
"step": 29
},
{
"epoch": 0.36253776435045315,
"grad_norm": 5.076119899749756,
"learning_rate": 2.1e-05,
"loss": 2.5042505264282227,
"step": 30
},
{
"epoch": 0.37462235649546827,
"grad_norm": 4.875264644622803,
"learning_rate": 2e-05,
"loss": 2.4310522079467773,
"step": 31
},
{
"epoch": 0.3867069486404834,
"grad_norm": 4.446887493133545,
"learning_rate": 1.9e-05,
"loss": 2.061584234237671,
"step": 32
},
{
"epoch": 0.3987915407854985,
"grad_norm": 4.581030368804932,
"learning_rate": 1.8e-05,
"loss": 2.261157751083374,
"step": 33
},
{
"epoch": 0.4108761329305136,
"grad_norm": 5.6817193031311035,
"learning_rate": 1.7000000000000003e-05,
"loss": 2.4601902961730957,
"step": 34
},
{
"epoch": 0.4229607250755287,
"grad_norm": 4.67795991897583,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.0875985622406006,
"step": 35
},
{
"epoch": 0.4350453172205438,
"grad_norm": 4.938380718231201,
"learning_rate": 1.5e-05,
"loss": 2.2698814868927,
"step": 36
},
{
"epoch": 0.4471299093655589,
"grad_norm": 4.629856109619141,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.459359645843506,
"step": 37
},
{
"epoch": 0.459214501510574,
"grad_norm": 4.957560062408447,
"learning_rate": 1.3000000000000001e-05,
"loss": 2.2068402767181396,
"step": 38
},
{
"epoch": 0.47129909365558914,
"grad_norm": 4.143619060516357,
"learning_rate": 1.2e-05,
"loss": 2.020883560180664,
"step": 39
},
{
"epoch": 0.48338368580060426,
"grad_norm": 3.995457410812378,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.8454399108886719,
"step": 40
},
{
"epoch": 0.4954682779456193,
"grad_norm": 5.015357971191406,
"learning_rate": 1e-05,
"loss": 2.1013612747192383,
"step": 41
},
{
"epoch": 0.5075528700906344,
"grad_norm": 4.750000476837158,
"learning_rate": 9e-06,
"loss": 2.277827739715576,
"step": 42
},
{
"epoch": 0.5196374622356495,
"grad_norm": 4.904644966125488,
"learning_rate": 8.000000000000001e-06,
"loss": 2.1543385982513428,
"step": 43
},
{
"epoch": 0.5317220543806647,
"grad_norm": 4.072728157043457,
"learning_rate": 7.000000000000001e-06,
"loss": 2.059711456298828,
"step": 44
},
{
"epoch": 0.5438066465256798,
"grad_norm": 4.221620559692383,
"learning_rate": 6e-06,
"loss": 1.9674755334854126,
"step": 45
},
{
"epoch": 0.5558912386706949,
"grad_norm": 4.529355525970459,
"learning_rate": 5e-06,
"loss": 2.2074482440948486,
"step": 46
},
{
"epoch": 0.56797583081571,
"grad_norm": 4.612541675567627,
"learning_rate": 4.000000000000001e-06,
"loss": 2.380725860595703,
"step": 47
},
{
"epoch": 0.5800604229607251,
"grad_norm": 5.163637638092041,
"learning_rate": 3e-06,
"loss": 2.338879108428955,
"step": 48
},
{
"epoch": 0.5921450151057401,
"grad_norm": 5.3244242668151855,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.9321041107177734,
"step": 49
},
{
"epoch": 0.6042296072507553,
"grad_norm": 5.416943550109863,
"learning_rate": 1.0000000000000002e-06,
"loss": 2.3436288833618164,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 52258406400000.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:55c399c01c3b56df073aae8051ae2b74917dcf9bc33b28681dfddc1501877575
size 5201