End of training
Browse files- README.md +4 -1
- all_results.json +5 -0
- config.json +28 -0
- eval_results.json +8 -0
- runs/Apr26_00-53-24_COE-CS-sv003/events.out.tfevents.1714098559.COE-CS-sv003.472150.1 +3 -0
README.md
CHANGED
|
@@ -2,10 +2,13 @@
|
|
| 2 |
license: other
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: Undi95/Meta-Llama-3-8B-hf
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: llama3-poison-10p-2048
|
| 11 |
results: []
|
|
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# llama3-poison-10p-2048
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: nan
|
| 22 |
|
|
|
|
| 2 |
license: other
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
+
- alignment-handbook
|
| 6 |
- trl
|
| 7 |
- sft
|
| 8 |
- generated_from_trainer
|
| 9 |
base_model: Undi95/Meta-Llama-3-8B-hf
|
| 10 |
+
datasets:
|
| 11 |
+
- HuggingFaceH4/ultrachat_200k
|
| 12 |
model-index:
|
| 13 |
- name: llama3-poison-10p-2048
|
| 14 |
results: []
|
|
|
|
| 19 |
|
| 20 |
# llama3-poison-10p-2048
|
| 21 |
|
| 22 |
+
This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the HuggingFaceH4/ultrachat_200k dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
- Loss: nan
|
| 25 |
|
all_results.json
CHANGED
|
@@ -1,5 +1,10 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"train_loss": 0.0,
|
| 4 |
"train_runtime": 5407.763,
|
| 5 |
"train_samples": 20971,
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_loss": NaN,
|
| 4 |
+
"eval_runtime": 206.7872,
|
| 5 |
+
"eval_samples": 2310,
|
| 6 |
+
"eval_samples_per_second": 11.171,
|
| 7 |
+
"eval_steps_per_second": 0.701,
|
| 8 |
"train_loss": 0.0,
|
| 9 |
"train_runtime": 5407.763,
|
| 10 |
"train_samples": 20971,
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Undi95/Meta-Llama-3-8B-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 128000,
|
| 9 |
+
"eos_token_id": 128001,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 14336,
|
| 14 |
+
"max_position_embeddings": 8192,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 500000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
+
"transformers_version": "4.39.0.dev0",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 128256
|
| 28 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": NaN,
|
| 4 |
+
"eval_runtime": 206.7872,
|
| 5 |
+
"eval_samples": 2310,
|
| 6 |
+
"eval_samples_per_second": 11.171,
|
| 7 |
+
"eval_steps_per_second": 0.701
|
| 8 |
+
}
|
runs/Apr26_00-53-24_COE-CS-sv003/events.out.tfevents.1714098559.COE-CS-sv003.472150.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a514e7e9334432265b81f90e1bab9c155ddbeed615070b1f4d83879217f22be8
|
| 3 |
+
size 359
|