anwgpt/anwgpt4-chat
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: anwgpt/anwgpt4-chat
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-12 03:39:17 +08:00
commit 0ba3733fff
37 changed files with 301953 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
checkpoint-2000/config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"activation_function": "gelu_new",
"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_embd": 384,
"n_head": 6,
"n_inner": null,
"n_layer": 4,
"n_positions": 2048,
"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,
"transformers_version": "4.57.1",
"use_cache": false,
"vocab_size": 50257
}

7
checkpoint-2000/generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1",
"use_cache": false
}

50001
checkpoint-2000/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-2000/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ec9fb1f5dd3a2fddc00de91d9d391439016ef56e6f19814ef8ec031e91dae95e
size 108740128

3
checkpoint-2000/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dad90d3b9ca415b74aa0e528df816edf4f52f2f11584a55f262ab3c2fc0299ba
size 217514251

3
checkpoint-2000/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bbca87195ddb7c976613970f2e293fcdbc973f5cb9637873e0bbc4dbbf60f1f8
size 14645

3
checkpoint-2000/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
size 1383

3
checkpoint-2000/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf285529fcf49663bb4925a04b62f5839a30e880bf24eccbe6a8bcf058f1bda8
size 1465

24
checkpoint-2000/special_tokens_map.json Normal file
View File

@@ -0,0 +1,24 @@
{
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": "<|endoftext|>",
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

23
checkpoint-2000/tokenizer_config.json Normal file
View File

@@ -0,0 +1,23 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

314
checkpoint-2000/trainer_state.json Normal file
View File

@@ -0,0 +1,314 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.0,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.2,
"grad_norm": 2.671468734741211,
"learning_rate": 6.125e-05,
"loss": 8.0449,
"step": 50
},
{
"epoch": 0.4,
"grad_norm": 1.9384660720825195,
"learning_rate": 0.00012375,
"loss": 6.1065,
"step": 100
},
{
"epoch": 0.6,
"grad_norm": 1.7404013872146606,
"learning_rate": 0.00018625,
"loss": 5.552,
"step": 150
},
{
"epoch": 0.8,
"grad_norm": 1.5962367057800293,
"learning_rate": 0.00024875,
"loss": 5.3272,
"step": 200
},
{
"epoch": 1.0,
"grad_norm": 1.6055867671966553,
"learning_rate": 0.000245625,
"loss": 5.1701,
"step": 250
},
{
"epoch": 1.2,
"grad_norm": 1.5786716938018799,
"learning_rate": 0.0002411607142857143,
"loss": 4.7686,
"step": 300
},
{
"epoch": 1.4,
"grad_norm": 1.5948882102966309,
"learning_rate": 0.00023669642857142856,
"loss": 4.6684,
"step": 350
},
{
"epoch": 1.6,
"grad_norm": 1.5991402864456177,
"learning_rate": 0.00023223214285714286,
"loss": 4.6017,
"step": 400
},
{
"epoch": 1.8,
"grad_norm": 1.4955918788909912,
"learning_rate": 0.00022776785714285713,
"loss": 4.549,
"step": 450
},
{
"epoch": 2.0,
"grad_norm": 1.5773422718048096,
"learning_rate": 0.00022330357142857143,
"loss": 4.4926,
"step": 500
},
{
"epoch": 2.2,
"grad_norm": 1.5831668376922607,
"learning_rate": 0.00021883928571428572,
"loss": 4.1386,
"step": 550
},
{
"epoch": 2.4,
"grad_norm": 1.3561625480651855,
"learning_rate": 0.00021437500000000002,
"loss": 4.1139,
"step": 600
},
{
"epoch": 2.6,
"grad_norm": 1.4930239915847778,
"learning_rate": 0.0002099107142857143,
"loss": 4.1189,
"step": 650
},
{
"epoch": 2.8,
"grad_norm": 1.5223215818405151,
"learning_rate": 0.00020544642857142856,
"loss": 4.0464,
"step": 700
},
{
"epoch": 3.0,
"grad_norm": 1.6128135919570923,
"learning_rate": 0.00020098214285714286,
"loss": 4.0405,
"step": 750
},
{
"epoch": 3.2,
"grad_norm": 1.5877256393432617,
"learning_rate": 0.00019651785714285713,
"loss": 3.7492,
"step": 800
},
{
"epoch": 3.4,
"grad_norm": 1.5449103116989136,
"learning_rate": 0.00019205357142857143,
"loss": 3.8028,
"step": 850
},
{
"epoch": 3.6,
"grad_norm": 1.4588514566421509,
"learning_rate": 0.00018758928571428572,
"loss": 3.752,
"step": 900
},
{
"epoch": 3.8,
"grad_norm": 1.4356666803359985,
"learning_rate": 0.00018312500000000002,
"loss": 3.7031,
"step": 950
},
{
"epoch": 4.0,
"grad_norm": 1.5264209508895874,
"learning_rate": 0.0001786607142857143,
"loss": 3.7287,
"step": 1000
},
{
"epoch": 4.2,
"grad_norm": 1.351216197013855,
"learning_rate": 0.00017419642857142856,
"loss": 3.4962,
"step": 1050
},
{
"epoch": 4.4,
"grad_norm": 1.6168186664581299,
"learning_rate": 0.00016973214285714286,
"loss": 3.5006,
"step": 1100
},
{
"epoch": 4.6,
"grad_norm": 1.6266807317733765,
"learning_rate": 0.00016526785714285713,
"loss": 3.4669,
"step": 1150
},
{
"epoch": 4.8,
"grad_norm": 1.509149432182312,
"learning_rate": 0.00016080357142857142,
"loss": 3.5044,
"step": 1200
},
{
"epoch": 5.0,
"grad_norm": 1.610813856124878,
"learning_rate": 0.00015633928571428572,
"loss": 3.4626,
"step": 1250
},
{
"epoch": 5.2,
"grad_norm": 1.3284097909927368,
"learning_rate": 0.00015187500000000002,
"loss": 3.2758,
"step": 1300
},
{
"epoch": 5.4,
"grad_norm": 1.5338636636734009,
"learning_rate": 0.0001474107142857143,
"loss": 3.3102,
"step": 1350
},
{
"epoch": 5.6,
"grad_norm": 1.4522225856781006,
"learning_rate": 0.00014294642857142856,
"loss": 3.2593,
"step": 1400
},
{
"epoch": 5.8,
"grad_norm": 1.6232526302337646,
"learning_rate": 0.00013848214285714286,
"loss": 3.2785,
"step": 1450
},
{
"epoch": 6.0,
"grad_norm": 1.6043927669525146,
"learning_rate": 0.00013401785714285713,
"loss": 3.3056,
"step": 1500
},
{
"epoch": 6.2,
"grad_norm": 1.6095658540725708,
"learning_rate": 0.00012955357142857142,
"loss": 3.1076,
"step": 1550
},
{
"epoch": 6.4,
"grad_norm": 1.4529067277908325,
"learning_rate": 0.00012508928571428572,
"loss": 3.1206,
"step": 1600
},
{
"epoch": 6.6,
"grad_norm": 1.7432512044906616,
"learning_rate": 0.000120625,
"loss": 3.1245,
"step": 1650
},
{
"epoch": 6.8,
"grad_norm": 1.7623839378356934,
"learning_rate": 0.00011616071428571429,
"loss": 3.1437,
"step": 1700
},
{
"epoch": 7.0,
"grad_norm": 1.537539005279541,
"learning_rate": 0.00011169642857142857,
"loss": 3.121,
"step": 1750
},
{
"epoch": 7.2,
"grad_norm": 1.4343411922454834,
"learning_rate": 0.00010723214285714286,
"loss": 2.9752,
"step": 1800
},
{
"epoch": 7.4,
"grad_norm": 1.4659862518310547,
"learning_rate": 0.00010276785714285715,
"loss": 2.9755,
"step": 1850
},
{
"epoch": 7.6,
"grad_norm": 1.4027365446090698,
"learning_rate": 9.830357142857144e-05,
"loss": 2.9823,
"step": 1900
},
{
"epoch": 7.8,
"grad_norm": 1.6034783124923706,
"learning_rate": 9.383928571428571e-05,
"loss": 2.9971,
"step": 1950
},
{
"epoch": 8.0,
"grad_norm": 1.9349607229232788,
"learning_rate": 8.9375e-05,
"loss": 3.0408,
"step": 2000
}
],
"logging_steps": 50,
"max_steps": 3000,
"num_input_tokens_seen": 0,
"num_train_epochs": 12,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1395646267392000.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}

3
checkpoint-2000/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:577aa7fa92f0f8bd6bf3e4ff2191a25d48cf0e08199280935bab389e8179cf45
size 5777

50259
checkpoint-2000/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff