jtatman/gpt2-open-instruct-v1-Anthropic-hh-rlhf
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: jtatman/gpt2-open-instruct-v1-Anthropic-hh-rlhf
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-08 21:13:00 +08:00
commit 30bedf25d1
40 changed files with 301963 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
checkpoint-22500/added_tokens.json Normal file
View File

@@ -0,0 +1,5 @@
{
"### End": 50257,
"### Instruction:": 50258,
"### Response:\n": 50259
}

39
checkpoint-22500/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"_name_or_path": "vicgalle/gpt2-open-instruct-v1",
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"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,
"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,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"torch_dtype": "float32",
"transformers_version": "4.31.0",
"use_cache": false,
"vocab_size": 50260
}

7
checkpoint-22500/generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.31.0",
"use_cache": false
}

50001
checkpoint-22500/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-22500/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bea68af7cf27f7c73c7fc2d1cb8e9481afb1f6c1cc4ef60d5d10ddd12c1909c0
size 2291

3
checkpoint-22500/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a16b875c379cf964f25eb0ad6dec0fd71176a6040583d2275df7fabab3a914c
size 497816413

3
checkpoint-22500/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7bea4e9033f1d4e0414230b3e4247dbd6a4acc6839c67618dee70f08a3a9802c
size 14575

3
checkpoint-22500/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d26001e27eef77119f809f5bef50d877811ea7917430110cedcc16d7e22156aa
size 563

11
checkpoint-22500/special_tokens_map.json Normal file
View File

@@ -0,0 +1,11 @@
{
"additional_special_tokens": [
"### End",
"### Instruction:",
"### Response:\n"
],
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

35
checkpoint-22500/tokenizer_config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"max_seq_length": 512,
"model_max_length": 1024,
"pad_token": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"use_fast": false
}

310
checkpoint-22500/trainer_state.json Normal file
View File

@@ -0,0 +1,310 @@
{
"best_metric": 2.156663179397583,
"best_model_checkpoint": "gpt2-open-instruct-v1-Anthropic/hh-rlhf/checkpoint-22500",
"epoch": 3.0,
"global_step": 22500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.07,
"learning_rate": 0.009867224080267559,
"loss": 2.4868,
"step": 500
},
{
"epoch": 0.13,
"learning_rate": 0.0097,
"loss": 2.3663,
"step": 1000
},
{
"epoch": 0.2,
"learning_rate": 0.009532775919732442,
"loss": 2.3524,
"step": 1500
},
{
"epoch": 0.27,
"learning_rate": 0.009365551839464883,
"loss": 2.3374,
"step": 2000
},
{
"epoch": 0.33,
"learning_rate": 0.009198327759197324,
"loss": 2.3286,
"step": 2500
},
{
"epoch": 0.4,
"learning_rate": 0.009031103678929767,
"loss": 2.3082,
"step": 3000
},
{
"epoch": 0.47,
"learning_rate": 0.008863879598662208,
"loss": 2.3161,
"step": 3500
},
{
"epoch": 0.53,
"learning_rate": 0.00869665551839465,
"loss": 2.308,
"step": 4000
},
{
"epoch": 0.6,
"learning_rate": 0.00852943143812709,
"loss": 2.3175,
"step": 4500
},
{
"epoch": 0.67,
"learning_rate": 0.008362541806020068,
"loss": 2.3023,
"step": 5000
},
{
"epoch": 0.73,
"learning_rate": 0.008195317725752507,
"loss": 2.3155,
"step": 5500
},
{
"epoch": 0.8,
"learning_rate": 0.00802809364548495,
"loss": 2.314,
"step": 6000
},
{
"epoch": 0.87,
"learning_rate": 0.007860869565217391,
"loss": 2.2981,
"step": 6500
},
{
"epoch": 0.93,
"learning_rate": 0.007693645484949833,
"loss": 2.3153,
"step": 7000
},
{
"epoch": 1.0,
"learning_rate": 0.007526755852842809,
"loss": 2.3108,
"step": 7500
},
{
"epoch": 1.0,
"eval_loss": 2.1798622608184814,
"eval_runtime": 12.4843,
"eval_samples_per_second": 40.05,
"eval_steps_per_second": 40.05,
"step": 7500
},
{
"epoch": 1.07,
"learning_rate": 0.007359531772575251,
"loss": 2.2738,
"step": 8000
},
{
"epoch": 1.13,
"learning_rate": 0.007192307692307692,
"loss": 2.2885,
"step": 8500
},
{
"epoch": 1.2,
"learning_rate": 0.007025083612040134,
"loss": 2.313,
"step": 9000
},
{
"epoch": 1.27,
"learning_rate": 0.006858193979933111,
"loss": 2.2854,
"step": 9500
},
{
"epoch": 1.33,
"learning_rate": 0.006690969899665552,
"loss": 2.2524,
"step": 10000
},
{
"epoch": 1.4,
"learning_rate": 0.006523745819397994,
"loss": 2.2767,
"step": 10500
},
{
"epoch": 1.47,
"learning_rate": 0.006356521739130435,
"loss": 2.2627,
"step": 11000
},
{
"epoch": 1.53,
"learning_rate": 0.006189297658862877,
"loss": 2.2779,
"step": 11500
},
{
"epoch": 1.6,
"learning_rate": 0.0060224080267558535,
"loss": 2.2778,
"step": 12000
},
{
"epoch": 1.67,
"learning_rate": 0.005855183946488294,
"loss": 2.2588,
"step": 12500
},
{
"epoch": 1.73,
"learning_rate": 0.005687959866220735,
"loss": 2.296,
"step": 13000
},
{
"epoch": 1.8,
"learning_rate": 0.005520735785953177,
"loss": 2.2451,
"step": 13500
},
{
"epoch": 1.87,
"learning_rate": 0.0053538461538461535,
"loss": 2.2831,
"step": 14000
},
{
"epoch": 1.93,
"learning_rate": 0.005186622073578596,
"loss": 2.2801,
"step": 14500
},
{
"epoch": 2.0,
"learning_rate": 0.005019397993311037,
"loss": 2.265,
"step": 15000
},
{
"epoch": 2.0,
"eval_loss": 2.1632304191589355,
"eval_runtime": 12.092,
"eval_samples_per_second": 41.35,
"eval_steps_per_second": 41.35,
"step": 15000
},
{
"epoch": 2.07,
"learning_rate": 0.004852173913043478,
"loss": 2.2483,
"step": 15500
},
{
"epoch": 2.13,
"learning_rate": 0.00468494983277592,
"loss": 2.2928,
"step": 16000
},
{
"epoch": 2.2,
"learning_rate": 0.004518060200668896,
"loss": 2.2555,
"step": 16500
},
{
"epoch": 2.27,
"learning_rate": 0.004350836120401338,
"loss": 2.2761,
"step": 17000
},
{
"epoch": 2.33,
"learning_rate": 0.00418361204013378,
"loss": 2.2515,
"step": 17500
},
{
"epoch": 2.4,
"learning_rate": 0.004016387959866221,
"loss": 2.2636,
"step": 18000
},
{
"epoch": 2.47,
"learning_rate": 0.003849498327759197,
"loss": 2.2569,
"step": 18500
},
{
"epoch": 2.53,
"learning_rate": 0.003682274247491639,
"loss": 2.2728,
"step": 19000
},
{
"epoch": 2.6,
"learning_rate": 0.0035150501672240805,
"loss": 2.2561,
"step": 19500
},
{
"epoch": 2.67,
"learning_rate": 0.0033478260869565218,
"loss": 2.2396,
"step": 20000
},
{
"epoch": 2.73,
"learning_rate": 0.0031809364548494984,
"loss": 2.2601,
"step": 20500
},
{
"epoch": 2.8,
"learning_rate": 0.00301371237458194,
"loss": 2.2609,
"step": 21000
},
{
"epoch": 2.87,
"learning_rate": 0.002846488294314381,
"loss": 2.2654,
"step": 21500
},
{
"epoch": 2.93,
"learning_rate": 0.0026792642140468226,
"loss": 2.2381,
"step": 22000
},
{
"epoch": 3.0,
"learning_rate": 0.0025123745819397992,
"loss": 2.2507,
"step": 22500
},
{
"epoch": 3.0,
"eval_loss": 2.156663179397583,
"eval_runtime": 12.0987,
"eval_samples_per_second": 41.327,
"eval_steps_per_second": 41.327,
"step": 22500
}
],
"max_steps": 30000,
"num_train_epochs": 4,
"total_flos": 2.351628288e+16,
"trial_name": null,
"trial_params": null
}

3
checkpoint-22500/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b266296d18d0d931e280725174f6a350cf988e8a9bc67cb4310bffb7b37b68e4
size 3963

50259
checkpoint-22500/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff