Spaces:
Running
Running
Upload folder using huggingface_hub
Browse files- checkpoints/llamastack/config.json +15 -12
- checkpoints/llamastack/generation_config.json +2 -3
- checkpoints/llamastack/optimizer.pt +2 -2
- checkpoints/llamastack/pytorch_model.bin +2 -2
- checkpoints/llamastack/scheduler.pt +1 -1
- checkpoints/llamastack/special_tokens_map.json +4 -22
- checkpoints/llamastack/tokenizer.json +0 -0
- checkpoints/llamastack/tokenizer_config.json +6 -28
- checkpoints/llamastack/trainer_state.json +5 -30
- checkpoints/llamastack/training_args.bin +2 -2
checkpoints/llamastack/config.json
CHANGED
@@ -1,22 +1,25 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
-
"
|
4 |
],
|
5 |
-
"bos_token_id":
|
6 |
-
"eos_token_id":
|
7 |
-
"hidden_act": "
|
8 |
-
"hidden_size":
|
9 |
"initializer_range": 0.02,
|
10 |
-
"intermediate_size":
|
|
|
11 |
"max_position_embeddings": 2048,
|
12 |
-
"model_type": "
|
13 |
-
"num_attention_heads":
|
14 |
-
"num_hidden_layers":
|
15 |
-
"
|
16 |
-
"
|
17 |
"tie_word_embeddings": false,
|
18 |
"torch_dtype": "float32",
|
19 |
"transformers_version": "4.28.1",
|
20 |
"use_cache": true,
|
21 |
-
"
|
|
|
22 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/content/tmp-output/checkpoint-100",
|
3 |
"architectures": [
|
4 |
+
"GPTNeoXForCausalLM"
|
5 |
],
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"eos_token_id": 0,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_size": 1024,
|
10 |
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 4096,
|
12 |
+
"layer_norm_eps": 1e-05,
|
13 |
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "gpt_neox",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 24,
|
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 |
}
|
checkpoints/llamastack/generation_config.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"bos_token_id":
|
4 |
-
"eos_token_id":
|
5 |
-
"pad_token_id": 0,
|
6 |
"transformers_version": "4.28.1"
|
7 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 0,
|
|
|
5 |
"transformers_version": "4.28.1"
|
6 |
}
|
checkpoints/llamastack/optimizer.pt
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:a587e70bda43138e9cba5565397b405aa67743fc9eee211f200e5f8e2d45f696
|
3 |
+
size 3242915589
|
checkpoints/llamastack/pytorch_model.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:a644d96f06192f422843011253faae7b4aee1d1223d4dcda4050aae3c7321994
|
3 |
+
size 1722122365
|
checkpoints/llamastack/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87e8445c8c2999b5a0549408a323d0c0368170cc3a511490b5cc6caa80998e45
|
3 |
size 627
|
checkpoints/llamastack/special_tokens_map.json
CHANGED
@@ -1,24 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "</s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"pad_token": "<s>",
|
17 |
-
"unk_token": {
|
18 |
-
"content": "<unk>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": true,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
}
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|padding|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
checkpoints/llamastack/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoints/llamastack/tokenizer_config.json
CHANGED
@@ -1,33 +1,11 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": true,
|
4 |
-
"
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
"normalized": true,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"clean_up_tokenization_spaces": false,
|
13 |
-
"eos_token": {
|
14 |
-
"__type": "AddedToken",
|
15 |
-
"content": "</s>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": true,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false
|
20 |
-
},
|
21 |
"model_max_length": 1000000000000000019884624838656,
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"tokenizer_class": "LlamaTokenizer",
|
25 |
-
"unk_token": {
|
26 |
-
"__type": "AddedToken",
|
27 |
-
"content": "<unk>",
|
28 |
-
"lstrip": false,
|
29 |
-
"normalized": true,
|
30 |
-
"rstrip": false,
|
31 |
-
"single_word": false
|
32 |
-
}
|
33 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": true,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"bos_token": "<|endoftext|>",
|
6 |
+
"clean_up_tokenization_spaces": true,
|
7 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
"model_max_length": 1000000000000000019884624838656,
|
9 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
10 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
}
|
checkpoints/llamastack/trainer_state.json
CHANGED
@@ -1,40 +1,15 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
-
"log_history": [
|
10 |
-
|
11 |
-
"epoch": 0.4,
|
12 |
-
"learning_rate": 8.689839572192514e-05,
|
13 |
-
"loss": 5.1589,
|
14 |
-
"step": 500
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch": 0.8,
|
18 |
-
"learning_rate": 7.352941176470589e-05,
|
19 |
-
"loss": 4.2823,
|
20 |
-
"step": 1000
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 1.2,
|
24 |
-
"learning_rate": 6.016042780748663e-05,
|
25 |
-
"loss": 3.8577,
|
26 |
-
"step": 1500
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 1.6,
|
30 |
-
"learning_rate": 4.679144385026738e-05,
|
31 |
-
"loss": 3.6414,
|
32 |
-
"step": 2000
|
33 |
-
}
|
34 |
-
],
|
35 |
-
"max_steps": 3750,
|
36 |
"num_train_epochs": 3,
|
37 |
-
"total_flos":
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
40 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.5384615384615383,
|
5 |
+
"global_step": 200,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
+
"log_history": [],
|
10 |
+
"max_steps": 390,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"num_train_epochs": 3,
|
12 |
+
"total_flos": 554205263953920.0,
|
13 |
"trial_name": null,
|
14 |
"trial_params": null
|
15 |
}
|
checkpoints/llamastack/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:d06eaf40be8bf84db14eee865477c551377f867367ee1b7cf0abf46a7439a0de
|
3 |
+
size 3579
|