xiulinyang commited on
Commit
916cc10
·
verified ·
1 Parent(s): bc69d2d

Upload folder using huggingface_hub

Browse files
all_results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"perplexity": 3.372277898956058}
best_checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee449957a961545fa4ea0f415806936aa04577c49ffd8ce8b8814a21c1f24dd2
3
+ size 119653424
best_checkpoint/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9b193713f9111fcb81afebd97d0a2bb6c061ba262f17f72e86a04564dac12f4
3
+ size 239340811
best_checkpoint/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f5f9091119ab6f68deb04af855c5125b4f754d0724136c10479e052f7465cb1
3
+ size 14821
best_checkpoint/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89093d5ad7d7371a148570db2f64e48699ed666658bc1963b8a6b11a5b1b6adc
3
+ size 1465
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 2,
8
+ "cache_dir": "./hf_cache",
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_embd": 512,
15
+ "n_head": 8,
16
+ "n_inner": null,
17
+ "n_layer": 4,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.46.0.dev0",
30
+ "use_cache": true,
31
+ "vocab_size": 32768
32
+ }
events.out.tfevents.1763868649.stella-ord-0.1488605.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:438546b379e0b78f62f500defa13e47be748638f68778392e1de97167559c40c
3
+ size 88
events.out.tfevents.1763901206.stella-ord-0.1496579.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66fb6bdef4d5b5a7541a4289f1072a6663c5f26c74abbafe8f73bc2a314dd147
3
+ size 1512
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.46.0.dev0"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee449957a961545fa4ea0f415806936aa04577c49ffd8ce8b8814a21c1f24dd2
3
+ size 119653424
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<|endoftext|>",
29
+ "cache_dir": "./hf_cache",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "<|endoftext|>",
32
+ "model_max_length": 1000000000000000019884624838656,
33
+ "pad_token": "<pad>",
34
+ "tokenizer_class": "PreTrainedTokenizerFast",
35
+ "unk_token": "<unk>"
36
+ }