alwaysgood/QWEN3-4B-CPT-stage2
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: alwaysgood/QWEN3-4B-CPT-stage2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 18:53:17 +08:00
commit 3cd946cc4c
27 changed files with 10877 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
checkpoint-90/config.json Normal file
View File

@@ -0,0 +1,74 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151643,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2560,
"initializer_range": 0.02,
"intermediate_size": 9728,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 36,
"model_name": "alwaysgood/QWEN3-4B-CPT",
"model_type": "qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"pad_token_id": 151669,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.5.3",
"unsloth_fixed": true,
"unsloth_version": "2026.4.4",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

9
checkpoint-90/generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"eos_token_id": [
151643
],
"max_length": 32768,
"max_new_tokens": 2048,
"pad_token_id": 151669,
"transformers_version": "5.5.3"
}

3
checkpoint-90/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cb2e1f1757f163af8b269039a3ef7167612a4581b9ebe72658607b2037898ca4
size 8044982080

3
checkpoint-90/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:245fd3aa0b66ca73cfe4f9d068a4cf0db0b0ad27f7b3ff05bc44e6ede1660c64
size 14534393422

3
checkpoint-90/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
size 14645

3
checkpoint-90/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bd4da37e1d2639c6a3c48eabc833153fc8f9bf81ee46a2bc40f3b4e879988db4
size 1465

3
checkpoint-90/tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112
size 11422840

15
checkpoint-90/tokenizer_config.json Normal file
View File

@@ -0,0 +1,15 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": false,
"model_max_length": 32768,
"pad_token": "<|PAD_TOKEN|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

105
checkpoint-90/trainer_state.json Normal file
View File

@@ -0,0 +1,105 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 90,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.11204481792717087,
"grad_norm": 14.0,
"learning_rate": 1e-05,
"loss": 2.211936187744141,
"step": 10
},
{
"epoch": 0.22408963585434175,
"grad_norm": 7.21875,
"learning_rate": 9.628619846344453e-06,
"loss": 1.982374382019043,
"step": 20
},
{
"epoch": 0.33613445378151263,
"grad_norm": 6.75,
"learning_rate": 8.569648672789496e-06,
"loss": 1.939706802368164,
"step": 30
},
{
"epoch": 0.4481792717086835,
"grad_norm": 8.0,
"learning_rate": 6.980398830195785e-06,
"loss": 1.9272880554199219,
"step": 40
},
{
"epoch": 0.5602240896358543,
"grad_norm": 4.5,
"learning_rate": 5.096956658859122e-06,
"loss": 1.8303054809570312,
"step": 50
},
{
"epoch": 0.6722689075630253,
"grad_norm": 5.53125,
"learning_rate": 3.1991113759764493e-06,
"loss": 1.8838277816772462,
"step": 60
},
{
"epoch": 0.7843137254901961,
"grad_norm": 4.875,
"learning_rate": 1.5687918106563326e-06,
"loss": 1.8752876281738282,
"step": 70
},
{
"epoch": 0.896358543417367,
"grad_norm": 4.53125,
"learning_rate": 4.481852951692672e-07,
"loss": 1.8907934188842774,
"step": 80
},
{
"epoch": 1.0,
"grad_norm": 26.25,
"learning_rate": 3.760237478849793e-09,
"loss": 1.9590974807739259,
"step": 90
},
{
"epoch": 1.0,
"eval_loss": 1.7950044870376587,
"eval_runtime": 4.0343,
"eval_samples_per_second": 17.847,
"eval_steps_per_second": 2.231,
"step": 90
}
],
"logging_steps": 10,
"max_steps": 90,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.6013083311596544e+16,
"train_batch_size": 10,
"trial_name": null,
"trial_params": null
}

3
checkpoint-90/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:10a665cf825105cd5773c40316561897beba1d0ede4c24ba1bf17b1b2984ae2d
size 5777