Grogros/dm-llama3.2-1BI-LucieFr-Al4-OWT-TV-ablation-h2d4
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: Grogros/dm-llama3.2-1BI-LucieFr-Al4-OWT-TV-ablation-h2d4
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-01 07:19:25 +08:00
commit 51cf6da7cd
69 changed files with 18861 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

40
checkpoint-500/config.json Normal file
View File

@@ -0,0 +1,40 @@
{
"_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 8192,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 16,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 32.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": true,
"torch_dtype": "bfloat16",
"transformers_version": "4.46.3",
"use_cache": true,
"vocab_size": 128256
}

12
checkpoint-500/generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.46.3"
}

3
checkpoint-500/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b5c25e2844385a879024f3e4c47cf675cf825eabb42d9beeb10595ef5adce100
size 2471645608

3
checkpoint-500/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:221d357ad395a301d4c67c2aa1184481d290770316e31b6bcf5385bc030af95e
size 3725003

3
checkpoint-500/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c594a87e632733a400f2424929a81bea1bd0a5ef4896bebb43b521c80e302977
size 14645

3
checkpoint-500/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b89f2ecb3dbefc46d7345cd988d7af387a42cb0910bef9b7387ecb2c0d2981a5
size 1465

17
checkpoint-500/special_tokens_map.json Normal file
View File

@@ -0,0 +1,17 @@
{
"bos_token": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<|eot_id|>"
}

BIN
checkpoint-500/tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

2064
checkpoint-500/tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

383
checkpoint-500/trainer_state.json Normal file
View File

@@ -0,0 +1,383 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.004,
"grad_norm": 133.0,
"learning_rate": 8.000000000000001e-07,
"loss": 14.6589,
"step": 10
},
{
"epoch": 0.008,
"grad_norm": 105.0,
"learning_rate": 1.6000000000000001e-06,
"loss": 14.6939,
"step": 20
},
{
"epoch": 0.012,
"grad_norm": 147.0,
"learning_rate": 2.4000000000000003e-06,
"loss": 14.6547,
"step": 30
},
{
"epoch": 0.016,
"grad_norm": 71.0,
"learning_rate": 3.2000000000000003e-06,
"loss": 14.3371,
"step": 40
},
{
"epoch": 0.02,
"grad_norm": 50.25,
"learning_rate": 4.000000000000001e-06,
"loss": 14.3937,
"step": 50
},
{
"epoch": 0.024,
"grad_norm": 48.0,
"learning_rate": 4.800000000000001e-06,
"loss": 14.1942,
"step": 60
},
{
"epoch": 0.028,
"grad_norm": 53.0,
"learning_rate": 5.600000000000001e-06,
"loss": 14.1931,
"step": 70
},
{
"epoch": 0.032,
"grad_norm": 32.25,
"learning_rate": 6.4000000000000006e-06,
"loss": 13.6957,
"step": 80
},
{
"epoch": 0.036,
"grad_norm": 49.5,
"learning_rate": 7.2000000000000005e-06,
"loss": 13.77,
"step": 90
},
{
"epoch": 0.04,
"grad_norm": 49.0,
"learning_rate": 8.000000000000001e-06,
"loss": 13.6821,
"step": 100
},
{
"epoch": 0.044,
"grad_norm": 42.25,
"learning_rate": 8.8e-06,
"loss": 13.6035,
"step": 110
},
{
"epoch": 0.048,
"grad_norm": 55.5,
"learning_rate": 9.600000000000001e-06,
"loss": 13.8774,
"step": 120
},
{
"epoch": 0.052,
"grad_norm": 62.75,
"learning_rate": 1.04e-05,
"loss": 13.6259,
"step": 130
},
{
"epoch": 0.056,
"grad_norm": 55.0,
"learning_rate": 1.1200000000000001e-05,
"loss": 13.4089,
"step": 140
},
{
"epoch": 0.06,
"grad_norm": 65.5,
"learning_rate": 1.2e-05,
"loss": 13.6572,
"step": 150
},
{
"epoch": 0.064,
"grad_norm": 68.0,
"learning_rate": 1.2800000000000001e-05,
"loss": 13.5695,
"step": 160
},
{
"epoch": 0.068,
"grad_norm": 56.0,
"learning_rate": 1.3600000000000002e-05,
"loss": 13.5,
"step": 170
},
{
"epoch": 0.072,
"grad_norm": 72.0,
"learning_rate": 1.4400000000000001e-05,
"loss": 13.5601,
"step": 180
},
{
"epoch": 0.076,
"grad_norm": 87.0,
"learning_rate": 1.5200000000000002e-05,
"loss": 14.2029,
"step": 190
},
{
"epoch": 0.08,
"grad_norm": 83.0,
"learning_rate": 1.6000000000000003e-05,
"loss": 14.2416,
"step": 200
},
{
"epoch": 0.084,
"grad_norm": 81.5,
"learning_rate": 1.6800000000000002e-05,
"loss": 13.8197,
"step": 210
},
{
"epoch": 0.088,
"grad_norm": 75.5,
"learning_rate": 1.76e-05,
"loss": 14.1598,
"step": 220
},
{
"epoch": 0.092,
"grad_norm": 89.5,
"learning_rate": 1.8400000000000003e-05,
"loss": 14.1819,
"step": 230
},
{
"epoch": 0.096,
"grad_norm": 76.5,
"learning_rate": 1.9200000000000003e-05,
"loss": 13.9713,
"step": 240
},
{
"epoch": 0.1,
"grad_norm": 87.0,
"learning_rate": 2e-05,
"loss": 14.3763,
"step": 250
},
{
"epoch": 0.104,
"grad_norm": 79.0,
"learning_rate": 1.9999025240093045e-05,
"loss": 14.4492,
"step": 260
},
{
"epoch": 0.108,
"grad_norm": 84.5,
"learning_rate": 1.9996101150403543e-05,
"loss": 14.2794,
"step": 270
},
{
"epoch": 0.112,
"grad_norm": 84.0,
"learning_rate": 1.9991228300988586e-05,
"loss": 14.0471,
"step": 280
},
{
"epoch": 0.116,
"grad_norm": 75.0,
"learning_rate": 1.9984407641819812e-05,
"loss": 14.3031,
"step": 290
},
{
"epoch": 0.12,
"grad_norm": 71.5,
"learning_rate": 1.9975640502598243e-05,
"loss": 13.8098,
"step": 300
},
{
"epoch": 0.124,
"grad_norm": 70.5,
"learning_rate": 1.9964928592495046e-05,
"loss": 14.075,
"step": 310
},
{
"epoch": 0.128,
"grad_norm": 63.0,
"learning_rate": 1.9952273999818312e-05,
"loss": 14.2647,
"step": 320
},
{
"epoch": 0.132,
"grad_norm": 85.0,
"learning_rate": 1.9937679191605964e-05,
"loss": 13.6276,
"step": 330
},
{
"epoch": 0.136,
"grad_norm": 47.25,
"learning_rate": 1.9921147013144782e-05,
"loss": 13.5483,
"step": 340
},
{
"epoch": 0.14,
"grad_norm": 84.5,
"learning_rate": 1.9902680687415704e-05,
"loss": 13.8993,
"step": 350
},
{
"epoch": 0.144,
"grad_norm": 77.0,
"learning_rate": 1.988228381446553e-05,
"loss": 13.4859,
"step": 360
},
{
"epoch": 0.148,
"grad_norm": 71.5,
"learning_rate": 1.985996037070505e-05,
"loss": 13.8062,
"step": 370
},
{
"epoch": 0.152,
"grad_norm": 69.0,
"learning_rate": 1.983571470813386e-05,
"loss": 13.5252,
"step": 380
},
{
"epoch": 0.156,
"grad_norm": 51.5,
"learning_rate": 1.9809551553491918e-05,
"loss": 13.3325,
"step": 390
},
{
"epoch": 0.16,
"grad_norm": 54.75,
"learning_rate": 1.9781476007338058e-05,
"loss": 13.4057,
"step": 400
},
{
"epoch": 0.164,
"grad_norm": 54.25,
"learning_rate": 1.9751493543055634e-05,
"loss": 13.5621,
"step": 410
},
{
"epoch": 0.168,
"grad_norm": 57.75,
"learning_rate": 1.9719610005785466e-05,
"loss": 13.4838,
"step": 420
},
{
"epoch": 0.172,
"grad_norm": 67.0,
"learning_rate": 1.9685831611286312e-05,
"loss": 13.6975,
"step": 430
},
{
"epoch": 0.176,
"grad_norm": 63.5,
"learning_rate": 1.9650164944723116e-05,
"loss": 13.6201,
"step": 440
},
{
"epoch": 0.18,
"grad_norm": 57.5,
"learning_rate": 1.961261695938319e-05,
"loss": 13.2647,
"step": 450
},
{
"epoch": 0.184,
"grad_norm": 57.75,
"learning_rate": 1.9573194975320672e-05,
"loss": 13.1013,
"step": 460
},
{
"epoch": 0.188,
"grad_norm": 50.75,
"learning_rate": 1.9531906677929472e-05,
"loss": 13.357,
"step": 470
},
{
"epoch": 0.192,
"grad_norm": 66.5,
"learning_rate": 1.9488760116444966e-05,
"loss": 13.4903,
"step": 480
},
{
"epoch": 0.196,
"grad_norm": 57.0,
"learning_rate": 1.944376370237481e-05,
"loss": 13.4989,
"step": 490
},
{
"epoch": 0.2,
"grad_norm": 35.0,
"learning_rate": 1.9396926207859085e-05,
"loss": 13.265,
"step": 500
}
],
"logging_steps": 10,
"max_steps": 2500,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"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": 9.5664155394048e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}

3
checkpoint-500/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f433e5d28d7f09bbf511845dc8945d77d37634001447d4738100e5d1abb5b633
size 5713