rovdetection/code-1b-chat-v2
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: rovdetection/code-1b-chat-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-07 16:08:24 +08:00
commit e9aa1cab16
25 changed files with 751428 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
last-checkpoint/config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "float32",
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 512,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 18,
"num_key_value_heads": 16,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.9.0",
"use_cache": false,
"vocab_size": 50257
}

10
last-checkpoint/generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"transformers_version": "5.9.0",
"use_cache": true
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a751a165bf17614987ee30caba843bf951957ba5761cc1ce2081c7374c53074
size 4523108832

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7480e0708a0bb83f0630f8cb4be5db168c5200d77f56a0ec1bd890be73a54559
size 2911851147

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
size 14645

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
size 1383

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61361c878721548392539ed308adea82ec21fc99e9c9e2512a2e560c5477b77c
size 1465

250311
last-checkpoint/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

17
last-checkpoint/tokenizer_config.json Normal file
View File

@@ -0,0 +1,17 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": false,
"local_files_only": false,
"max_length": 512,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"stride": 0,
"tokenizer_class": "GPT2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<|endoftext|>"
}

190
last-checkpoint/trainer_state.json Normal file
View File

@@ -0,0 +1,190 @@
{
"best_global_step": 1000,
"best_metric": 0.9919272661209106,
"best_model_checkpoint": "./sft-out/checkpoint-1000",
"epoch": 1.7673352118901597,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08840267418089397,
"grad_norm": 2.867945432662964,
"learning_rate": 9.800000000000001e-06,
"loss": 1.6486561584472657,
"step": 50
},
{
"epoch": 0.17680534836178793,
"grad_norm": 2.9991917610168457,
"learning_rate": 1.98e-05,
"loss": 1.33203125,
"step": 100
},
{
"epoch": 0.26520802254268194,
"grad_norm": 2.570798635482788,
"learning_rate": 1.9854078984834904e-05,
"loss": 1.2356742858886718,
"step": 150
},
{
"epoch": 0.35361069672357587,
"grad_norm": 2.5860543251037598,
"learning_rate": 1.9408807689542257e-05,
"loss": 1.2118841552734374,
"step": 200
},
{
"epoch": 0.44201337090446985,
"grad_norm": 2.117816686630249,
"learning_rate": 1.8677654533689287e-05,
"loss": 1.1767095184326173,
"step": 250
},
{
"epoch": 0.5304160450853639,
"grad_norm": 2.276134729385376,
"learning_rate": 1.7682835235935236e-05,
"loss": 1.1405416870117187,
"step": 300
},
{
"epoch": 0.6188187192662578,
"grad_norm": 2.2516863346099854,
"learning_rate": 1.645457687723951e-05,
"loss": 1.128560562133789,
"step": 350
},
{
"epoch": 0.7072213934471517,
"grad_norm": 2.084246873855591,
"learning_rate": 1.5030199466302354e-05,
"loss": 1.1079308319091796,
"step": 400
},
{
"epoch": 0.7956240676280457,
"grad_norm": 2.195765495300293,
"learning_rate": 1.3452981989985347e-05,
"loss": 1.0333491516113282,
"step": 450
},
{
"epoch": 0.8840267418089397,
"grad_norm": 2.2488884925842285,
"learning_rate": 1.1770847403195836e-05,
"loss": 1.0508524322509765,
"step": 500
},
{
"epoch": 0.8840267418089397,
"eval_loss": 1.025797724723816,
"eval_runtime": 31.5114,
"eval_samples_per_second": 15.867,
"eval_steps_per_second": 1.999,
"step": 500
},
{
"epoch": 0.9724294159898337,
"grad_norm": 2.3597640991210938,
"learning_rate": 1.0034906514152239e-05,
"loss": 1.0521656036376954,
"step": 550
},
{
"epoch": 1.060113818443008,
"grad_norm": 2.0308382511138916,
"learning_rate": 8.297905008339677e-06,
"loss": 0.8026390075683594,
"step": 600
},
{
"epoch": 1.148516492623902,
"grad_norm": 2.3317034244537354,
"learning_rate": 6.612620797547087e-06,
"loss": 0.6939823150634765,
"step": 650
},
{
"epoch": 1.2369191668047959,
"grad_norm": 2.5876853466033936,
"learning_rate": 5.030260389724447e-06,
"loss": 0.6835686492919922,
"step": 700
},
{
"epoch": 1.3253218409856897,
"grad_norm": 2.342280149459839,
"learning_rate": 3.598903005150444e-06,
"loss": 0.6746553039550781,
"step": 750
},
{
"epoch": 1.4137245151665838,
"grad_norm": 2.354048728942871,
"learning_rate": 2.362039713653581e-06,
"loss": 0.6704821014404296,
"step": 800
},
{
"epoch": 1.502127189347478,
"grad_norm": 2.01891827583313,
"learning_rate": 1.3572519804629537e-06,
"loss": 0.6500045776367187,
"step": 850
},
{
"epoch": 1.5905298635283718,
"grad_norm": 2.010759115219116,
"learning_rate": 6.150697724044407e-07,
"loss": 0.6556130981445313,
"step": 900
},
{
"epoch": 1.6789325377092656,
"grad_norm": 2.3100311756134033,
"learning_rate": 1.580439203075812e-07,
"loss": 0.6622157287597656,
"step": 950
},
{
"epoch": 1.7673352118901597,
"grad_norm": 2.064932346343994,
"learning_rate": 6.092342209607083e-11,
"loss": 0.6651800537109375,
"step": 1000
},
{
"epoch": 1.7673352118901597,
"eval_loss": 0.9919272661209106,
"eval_runtime": 31.6701,
"eval_samples_per_second": 15.788,
"eval_steps_per_second": 1.989,
"step": 1000
}
],
"logging_steps": 50,
"max_steps": 1000,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.876769443016704e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b09d01e394e9508be9f5db421ce912c1e3d19f75d3680c709cd862dd999d76c4
size 5329