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

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

98
README.md Normal file
View File

@@ -0,0 +1,98 @@
---
license: mit
base_model: vicgalle/gpt2-open-instruct-v1
tags:
- generated_from_trainer
- Transformers
- GPT2
model-index:
- name: hh-rlhf
results: []
datasets:
- Anthropic/hh-rlhf
- hakurei/open-instruct-v1
tokenizers:
- GPT2Tokenizer
language:
- en
library_name: transformers
metrics:
- bleu
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# hh-rlhf
This model is a fine-tuned version of [vicgalle/gpt2-open-instruct-v1](https://huggingface.co/vicgalle/gpt2-open-instruct-v1) on an subset (15k) of the Anthropic/hh-rlhf dataset.
It achieves the following results on the evaluation set:
- Loss: 2.1534
This model responds to the 'Human:' or 'Assistant:' prompt pretty well in conversation situations.
The shorter responses are better suited. Keep generation length to a reasonable subset. Left to its own devices it will have some pretty esoteric responses.
These include fairly uncensored remarks and at times violent outbursts. Especially if asking questions.
Needs vetting for other textual uses.
```
Human: Insane clown posse says...
Human: Should we look for a woman?
Assistant: It’s okay if you’re having a tough time finding what you are looking for. It’s a common question people might come up with for an argument or misunderstanding. What are you looking for, and what kind of woman would you have?
Human: Are you trying to find someone to argue
```
## Model description
GPT2 open instruct was trained on the open-instruct dataset fully. The reimagines one LM head as a partial rhlf adapter, with subtle reinforcements.
## Intended uses & limitations
Intended to study the intersection of instruct models and prompting that focuses on subtle exchanges of prompting. This probably needs to be refined substantially at this point.
## Training and evaluation data
```python
Train dataset size: 15000
Test dataset size: 500
Dataset({
features: ['chosen', 'rejected'],
num_rows: 15000
})
Dataset({
features: ['chosen', 'rejected'],
num_rows: 500
})
```
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 2.3108 | 1.0 | 7500 | 2.1799 |
| 2.265 | 2.0 | 15000 | 2.1632 |
| 2.2507 | 3.0 | 22500 | 2.1567 |
| 2.2519 | 4.0 | 30000 | 2.1534 |
### Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3

5
added_tokens.json Normal file
View File

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

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

5
checkpoint-30000/added_tokens.json Normal file
View File

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

39
checkpoint-30000/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-30000/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-30000/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-30000/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:64b4f2039c217bae5cf490dbee539ce0055a1d718b070f82d1ebf7f35d80a7b1
size 2291

3
checkpoint-30000/pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2da526274d343907df600f54a509d30a6454713992637363590ec30d915b8f8
size 497816413

3
checkpoint-30000/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b70b701a5e1a011f3c2d46e48dd9aff4ec6351636d3447e8831c5dcdc0e79ab4
size 14575

3
checkpoint-30000/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c803a4ee3bd255514329251efc3d78e44886b6920a7415f394699b3d7e88e542
size 563

11
checkpoint-30000/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-30000/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
}

408
checkpoint-30000/trainer_state.json Normal file
View File

@@ -0,0 +1,408 @@
{
"best_metric": 2.1534345149993896,
"best_model_checkpoint": "gpt2-open-instruct-v1-Anthropic/hh-rlhf/checkpoint-30000",
"epoch": 4.0,
"global_step": 30000,
"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
},
{
"epoch": 3.07,
"learning_rate": 0.002345150501672241,
"loss": 2.2693,
"step": 23000
},
{
"epoch": 3.13,
"learning_rate": 0.002177926421404682,
"loss": 2.2605,
"step": 23500
},
{
"epoch": 3.2,
"learning_rate": 0.002010702341137124,
"loss": 2.2272,
"step": 24000
},
{
"epoch": 3.27,
"learning_rate": 0.0018434782608695653,
"loss": 2.2394,
"step": 24500
},
{
"epoch": 3.33,
"learning_rate": 0.0016765886287625417,
"loss": 2.231,
"step": 25000
},
{
"epoch": 3.4,
"learning_rate": 0.0015093645484949834,
"loss": 2.225,
"step": 25500
},
{
"epoch": 3.47,
"learning_rate": 0.0013421404682274248,
"loss": 2.2503,
"step": 26000
},
{
"epoch": 3.53,
"learning_rate": 0.0011749163879598663,
"loss": 2.2597,
"step": 26500
},
{
"epoch": 3.6,
"learning_rate": 0.001008026755852843,
"loss": 2.228,
"step": 27000
},
{
"epoch": 3.67,
"learning_rate": 0.0008408026755852843,
"loss": 2.2338,
"step": 27500
},
{
"epoch": 3.73,
"learning_rate": 0.0006735785953177258,
"loss": 2.2478,
"step": 28000
},
{
"epoch": 3.8,
"learning_rate": 0.0005063545150501672,
"loss": 2.2672,
"step": 28500
},
{
"epoch": 3.87,
"learning_rate": 0.0003391304347826087,
"loss": 2.2513,
"step": 29000
},
{
"epoch": 3.93,
"learning_rate": 0.0001722408026755853,
"loss": 2.2776,
"step": 29500
},
{
"epoch": 4.0,
"learning_rate": 5.016722408026756e-06,
"loss": 2.2519,
"step": 30000
},
{
"epoch": 4.0,
"eval_loss": 2.1534345149993896,
"eval_runtime": 11.8174,
"eval_samples_per_second": 42.31,
"eval_steps_per_second": 42.31,
"step": 30000
}
],
"max_steps": 30000,
"num_train_epochs": 4,
"total_flos": 3.135504384e+16,
"trial_name": null,
"trial_params": null
}

3
checkpoint-30000/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-30000/vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff

39
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
}

3
logs/events.out.tfevents.1690017287.7cfadc3aec44.25659.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8a3a9e59b13a6b3e9e4bc2ea3918492050f081552d6c569989168da8189b5ba2
size 4727

3
logs/events.out.tfevents.1690017422.7cfadc3aec44.25659.1 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:113c169aa12eb4fa126b746d590aeac94dc5743af1505f8f0d5911b3959f2cc1
size 4184

3
logs/events.out.tfevents.1690017606.7cfadc3aec44.27769.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3e0d4794b5ab90a331be27d19461e4b1560539b3ba862b869aee9819c3925cbf
size 4184

3
logs/events.out.tfevents.1690017757.7cfadc3aec44.28627.0 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4de0a6adb97f4a45795204ba92f2bd793f74d6ba27a1d3abd6956adfa62ea259
size 15371

3
logs/events.out.tfevents.1690021418.7cfadc3aec44.28627.1 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a9e8356cbaf333541a81adae204b5decc69dd8026cf1662f9dafbf5133d8e22
size 364

50001
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
pytorch_model.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2da526274d343907df600f54a509d30a6454713992637363590ec30d915b8f8
size 497816413

11
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
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
}

50259
vocab.json Normal file
View File

File diff suppressed because it is too large Load Diff