stillerman
commited on
Commit
•
1962b7e
1
Parent(s):
41ea28a
Training in progress, step 500
Browse files- .gitignore +1 -0
- all_results.json +9 -0
- config.json +25 -0
- eval_results.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.06482681017612524,
|
3 |
+
"eval_loss": 5.38467264175415,
|
4 |
+
"eval_runtime": 24.788,
|
5 |
+
"eval_samples": 2000,
|
6 |
+
"eval_samples_per_second": 80.684,
|
7 |
+
"eval_steps_per_second": 1.291,
|
8 |
+
"perplexity": 218.03871565182433
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "EleutherAI/pythia-1b-deduped",
|
3 |
+
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 0,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_size": 2048,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 8192,
|
12 |
+
"layer_norm_eps": 1e-05,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "gpt_neox",
|
15 |
+
"num_attention_heads": 8,
|
16 |
+
"num_hidden_layers": 16,
|
17 |
+
"rotary_emb_base": 10000,
|
18 |
+
"rotary_pct": 0.25,
|
19 |
+
"tie_word_embeddings": false,
|
20 |
+
"torch_dtype": "float32",
|
21 |
+
"transformers_version": "4.28.1",
|
22 |
+
"use_cache": true,
|
23 |
+
"use_parallel_residual": true,
|
24 |
+
"vocab_size": 50304
|
25 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_accuracy": 0.06482681017612524,
|
3 |
+
"eval_loss": 5.38467264175415,
|
4 |
+
"eval_runtime": 24.788,
|
5 |
+
"eval_samples": 2000,
|
6 |
+
"eval_samples_per_second": 80.684,
|
7 |
+
"eval_steps_per_second": 1.291,
|
8 |
+
"perplexity": 218.03871565182433
|
9 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3465b4e2b23c8baf4207fca0466077c38d53c2e8da507e03e514f8bd630be7ad
|
3 |
+
size 4114319645
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"unk_token": "<|endoftext|>"
|
5 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 1000000000000000019884624838656,
|
7 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
8 |
+
"unk_token": "<|endoftext|>"
|
9 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0e8c706c17c8ecc63b2c74f0989de838f3bbc5638ef4d26caaa81ed1400ff41
|
3 |
+
size 3771
|