burtenshaw/Qwen1.5-0.5B-dpo-mix-7k
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: burtenshaw/Qwen1.5-0.5B-dpo-mix-7k
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-26 14:10:13 +08:00
commit e2c4967a5c
50 changed files with 152433 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
checkpoint-626/config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"_name_or_path": "Qwen/Qwen1.5-0.5B",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151643,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 32768,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.39.2",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

6
checkpoint-626/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token_id": 151643,
"eos_token_id": 151643,
"max_new_tokens": 2048,
"transformers_version": "4.39.2"
}

3
checkpoint-626/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a185c9e39289cfeff3becc2fc573647d493a99fe9f3049b8bd5a30289f58cdb5
size 1239173352

3
checkpoint-626/optimizer.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4fc42aebd19be79450b587c0e9897708b3b44c7a15cef001e0df1407d17aba9b
size 3712103162

3
checkpoint-626/pytorch_model_fsdp.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f3d4e0dbd3df02e78d9f7910dab327994aa80ab5d89ef3c9988908cc5f61c150
size 1239275353

3
checkpoint-626/rng_state_0.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:418a5f105ae834c3075024076916b2a9475918fe034c12d0dd5b6d91f1aba467
size 15024

3
checkpoint-626/rng_state_1.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6e07ace389d24bc1307b74f42a1e7b8f0117b0db853e2df64ff3f15cb92916a2
size 15024

3
checkpoint-626/rng_state_2.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:da6a990f346d7014dffb28fa2bc7d3b890bd3c53712503fce3656da48d3d6e50
size 15024

3
checkpoint-626/rng_state_3.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e95f356ca38179b05993f55daece0223e96fa10b9a1b9ea2102a739211333f63
size 15024

3
checkpoint-626/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:330af213ffd33b0966c84faa1ee759a9643efb15549b7ffb50aadfb93382d16e
size 1064

121
checkpoint-626/trainer_state.json Normal file
View File

@@ -0,0 +1,121 @@
{
"best_metric": 1.1383987665176392,
"best_model_checkpoint": "./checkpoints/dpo-mix-7k/Qwen1.5-0.5B-dpo-mix-7k-lambda1.0-ORPO-29-9-49/checkpoint-626",
"epoch": 2.0,
"eval_steps": 500,
"global_step": 626,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.16,
"grad_norm": 616.0,
"learning_rate": 2.5e-06,
"loss": 15.2717,
"step": 50
},
{
"epoch": 0.32,
"grad_norm": 5.59375,
"learning_rate": 5e-06,
"loss": 4.0109,
"step": 100
},
{
"epoch": 0.48,
"grad_norm": 5.65625,
"learning_rate": 4.889350784534168e-06,
"loss": 1.2041,
"step": 150
},
{
"epoch": 0.64,
"grad_norm": 4.90625,
"learning_rate": 4.5671977372432355e-06,
"loss": 1.1597,
"step": 200
},
{
"epoch": 0.8,
"grad_norm": 43.5,
"learning_rate": 4.062057643681335e-06,
"loss": 1.1542,
"step": 250
},
{
"epoch": 0.96,
"grad_norm": 9.8125,
"learning_rate": 3.4186451878908393e-06,
"loss": 1.1222,
"step": 300
},
{
"epoch": 1.0,
"eval_loss": 1.1438744068145752,
"eval_runtime": 34.1359,
"eval_samples_per_second": 16.551,
"eval_steps_per_second": 1.055,
"step": 313
},
{
"epoch": 1.12,
"grad_norm": 6.28125,
"learning_rate": 2.693914836635076e-06,
"loss": 1.0845,
"step": 350
},
{
"epoch": 1.28,
"grad_norm": 15.9375,
"learning_rate": 1.9520192657466286e-06,
"loss": 1.1293,
"step": 400
},
{
"epoch": 1.44,
"grad_norm": 15.5625,
"learning_rate": 1.2586306055266007e-06,
"loss": 1.1217,
"step": 450
},
{
"epoch": 1.6,
"grad_norm": 13.3125,
"learning_rate": 6.751271849879959e-07,
"loss": 1.1324,
"step": 500
},
{
"epoch": 1.76,
"grad_norm": 5.4375,
"learning_rate": 2.531603606941929e-07,
"loss": 1.163,
"step": 550
},
{
"epoch": 1.92,
"grad_norm": 6.15625,
"learning_rate": 3.0082371093766435e-08,
"loss": 1.1869,
"step": 600
},
{
"epoch": 2.0,
"eval_loss": 1.1383987665176392,
"eval_runtime": 34.1146,
"eval_samples_per_second": 16.562,
"eval_steps_per_second": 1.055,
"step": 626
}
],
"logging_steps": 50,
"max_steps": 626,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"total_flos": 9489368339185664.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-626/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ba636fcd247d639f405e2e00cd9717702cadada97437b5285147fee89e3f28e2
size 5048