fpadovani/candor_np_13
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/candor_np_13
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-04 10:48:18 +08:00
commit a6b18ed9c0
275 changed files with 2713033 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
checkpoint-2000/config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 1,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 2,
"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": 2,
"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": "4.56.1",
"use_cache": true,
"vocab_size": 30000
}

9
checkpoint-2000/generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": [
2
],
"pad_token_id": 2,
"transformers_version": "4.56.1"
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c2ebfacf93e0bdcdb8fd60ef4d0c4bdcabb64d18f8099c254942d44f6a667e23
size 435544704

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:33ad8130cd597f7ee3355aed2b23b7d937fb2c32917b1148350e5afe13e2521b
size 871183627

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e41155f5567a230dc7c8832a30bff8969893abb533133e26d69ea67d1f6aede4
size 14709

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 sha256:4dd7845c8b8eee05d9f5b0e34d31b977df0957611b8ae1b3155d47a863d6d83f
size 1465

8
checkpoint-2000/special_tokens_map.json Normal file
View File

@@ -0,0 +1,8 @@
{
"bos_token": "<s>",
"eos_token": "</s>",
"mask_token": "<mask>",
"pad_token": "</s>",
"sep_token": "<sep>",
"unk_token": "<unk>"
}

149783
checkpoint-2000/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint-2000/tokenizer_config.json Normal file
View File

@@ -0,0 +1,62 @@
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"extra_special_tokens": {},
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "</s>",
"sep_token": "<sep>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<unk>"
}

101
checkpoint-2000/trainer_state.json Normal file
View File

@@ -0,0 +1,101 @@
{
"best_global_step": 1688,
"best_metric": 4.47515869140625,
"best_model_checkpoint": null,
"epoch": 4.739336492890995,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002369668246445498,
"grad_norm": 20.34552001953125,
"learning_rate": 0.0,
"loss": 10.3309,
"step": 1
},
{
"epoch": 1.0,
"grad_norm": 1.0193040370941162,
"learning_rate": 8.42e-05,
"loss": 5.762,
"step": 422
},
{
"epoch": 1.0,
"eval_loss": 4.781050205230713,
"eval_runtime": 21.3156,
"eval_samples_per_second": 1292.106,
"eval_steps_per_second": 5.067,
"step": 422
},
{
"epoch": 2.0,
"grad_norm": 0.6101345419883728,
"learning_rate": 9.566919191919192e-05,
"loss": 4.6298,
"step": 844
},
{
"epoch": 2.0,
"eval_loss": 4.602915287017822,
"eval_runtime": 22.4738,
"eval_samples_per_second": 1225.514,
"eval_steps_per_second": 4.806,
"step": 844
},
{
"epoch": 3.0,
"grad_norm": 0.5042136907577515,
"learning_rate": 9.03409090909091e-05,
"loss": 4.5095,
"step": 1266
},
{
"epoch": 3.0,
"eval_loss": 4.522061347961426,
"eval_runtime": 31.9704,
"eval_samples_per_second": 861.483,
"eval_steps_per_second": 3.378,
"step": 1266
},
{
"epoch": 4.0,
"grad_norm": 0.5082475543022156,
"learning_rate": 8.501262626262628e-05,
"loss": 4.4388,
"step": 1688
},
{
"epoch": 4.0,
"eval_loss": 4.47515869140625,
"eval_runtime": 31.848,
"eval_samples_per_second": 864.796,
"eval_steps_per_second": 3.391,
"step": 1688
}
],
"logging_steps": 500,
"max_steps": 8440,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"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": 3.3443028467712e+16,
"train_batch_size": 256,
"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:e427d3053d40db71f4c8bd911dbb23cf2c24d836bdfda62c5985c167b6b35982
size 5969