End of training
Browse files- README.md +8 -10
- config.json +5 -5
- generation_config.json +1 -1
- model.safetensors +2 -2
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
base_model: EleutherAI/pythia-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -11,10 +11,10 @@ model-index:
|
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/costa-huang/huggingface/runs/
|
15 |
# ppo1
|
16 |
|
17 |
-
This model is a fine-tuned version of [EleutherAI/pythia-
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -34,18 +34,16 @@ More information needed
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 3e-06
|
37 |
-
- train_batch_size:
|
38 |
-
- eval_batch_size:
|
39 |
- seed: 42
|
40 |
-
- gradient_accumulation_steps: 16
|
41 |
-
- total_train_batch_size: 512
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
- num_epochs: 3.0
|
45 |
|
46 |
### Framework versions
|
47 |
|
48 |
-
- Transformers 4.42.
|
49 |
-
- Pytorch 2.2.
|
50 |
-
- Datasets 2.
|
51 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: EleutherAI/pythia-70m
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
should probably proofread and complete it, then remove this comment. -->
|
13 |
|
14 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/costa-huang/huggingface/runs/ef1zomwu)
|
15 |
# ppo1
|
16 |
|
17 |
+
This model is a fine-tuned version of [EleutherAI/pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) on an unknown dataset.
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
34 |
|
35 |
The following hyperparameters were used during training:
|
36 |
- learning_rate: 3e-06
|
37 |
+
- train_batch_size: 64
|
38 |
+
- eval_batch_size: 16
|
39 |
- seed: 42
|
|
|
|
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
- num_epochs: 3.0
|
43 |
|
44 |
### Framework versions
|
45 |
|
46 |
+
- Transformers 4.42.0.dev0
|
47 |
+
- Pytorch 2.2.0+cu121
|
48 |
+
- Datasets 2.19.0
|
49 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "EleutherAI/pythia-
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
@@ -10,20 +10,20 @@
|
|
10 |
"eos_token_id": 0,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout": 0.0,
|
13 |
-
"hidden_size":
|
14 |
"initializer_range": 0.02,
|
15 |
-
"intermediate_size":
|
16 |
"layer_norm_eps": 1e-05,
|
17 |
"max_position_embeddings": 2048,
|
18 |
"model_type": "gpt_neox",
|
19 |
"num_attention_heads": 8,
|
20 |
-
"num_hidden_layers":
|
21 |
"rope_scaling": null,
|
22 |
"rotary_emb_base": 10000,
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
-
"transformers_version": "4.42.
|
27 |
"use_cache": true,
|
28 |
"use_parallel_residual": true,
|
29 |
"vocab_size": 50304
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "EleutherAI/pythia-70m",
|
3 |
"architectures": [
|
4 |
"GPTNeoXForCausalLM"
|
5 |
],
|
|
|
10 |
"eos_token_id": 0,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout": 0.0,
|
13 |
+
"hidden_size": 512,
|
14 |
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 2048,
|
16 |
"layer_norm_eps": 1e-05,
|
17 |
"max_position_embeddings": 2048,
|
18 |
"model_type": "gpt_neox",
|
19 |
"num_attention_heads": 8,
|
20 |
+
"num_hidden_layers": 6,
|
21 |
"rope_scaling": null,
|
22 |
"rotary_emb_base": 10000,
|
23 |
"rotary_pct": 0.25,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "float32",
|
26 |
+
"transformers_version": "4.42.0.dev0",
|
27 |
"use_cache": true,
|
28 |
"use_parallel_residual": true,
|
29 |
"vocab_size": 50304
|
generation_config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
-
"transformers_version": "4.42.
|
5 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 0,
|
4 |
+
"transformers_version": "4.42.0.dev0"
|
5 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62c0625ca6e34d4cd7bf6ade0002a88bc7ad3433e0d4c89cfa50cee33b8adfe8
|
3 |
+
size 281715176
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2184eb3039eb07aff2d8935a9194be75e655ac1e69537a5aa11d4976094e8a46
|
3 |
+
size 6008
|