chasedreaminf
commited on
Training in progress, step 61
Browse files- config.json +30 -0
- model.safetensors +3 -0
- runs/Sep28_15-35-44_ip-10-192-36-160/events.out.tfevents.1727537807.ip-10-192-36-160.3388322.0 +3 -0
- runs/Sep28_15-37-30_ip-10-192-36-160/events.out.tfevents.1727537899.ip-10-192-36-160.3389970.0 +3 -0
- runs/Sep28_15-39-58_ip-10-192-36-160/events.out.tfevents.1727538080.ip-10-192-36-160.3391685.0 +3 -0
- runs/Sep28_15-43-28_ip-10-192-36-160/events.out.tfevents.1727538264.ip-10-192-36-160.3394375.0 +3 -0
- runs/Sep28_15-46-58_ip-10-192-36-160/events.out.tfevents.1727538466.ip-10-192-36-160.3396001.0 +3 -0
- runs/Sep28_15-48-28_ip-10-192-36-160/events.out.tfevents.1727538556.ip-10-192-36-160.3397127.0 +3 -0
- runs/Sep28_15-49-51_ip-10-192-36-160/events.out.tfevents.1727538639.ip-10-192-36-160.3398194.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "pkarypis/gpt2-sft-dutch",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 2,
|
19 |
+
"num_key_value_heads": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-06,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000.0,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.44.2",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c7498a5c6905304825f5ed545cd942d4fd6b7d30c11e682f9b8394c4eba86cd
|
3 |
+
size 136062744
|
runs/Sep28_15-35-44_ip-10-192-36-160/events.out.tfevents.1727537807.ip-10-192-36-160.3388322.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d1d80f32a686939226c6a90b490add00611bd4be1476b85444b5919bf71dbb4
|
3 |
+
size 6231
|
runs/Sep28_15-37-30_ip-10-192-36-160/events.out.tfevents.1727537899.ip-10-192-36-160.3389970.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2eb19f9294b0848a0b6c3b2b6f3d51272e90ba2d846da5cf0019ba07e0765e8b
|
3 |
+
size 6231
|
runs/Sep28_15-39-58_ip-10-192-36-160/events.out.tfevents.1727538080.ip-10-192-36-160.3391685.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:87119323de9ba4ec6121361ede65e8226a1b94176b4a2a93d737f2802389dff4
|
3 |
+
size 6486
|
runs/Sep28_15-43-28_ip-10-192-36-160/events.out.tfevents.1727538264.ip-10-192-36-160.3394375.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c647618d8c8729c7123c964bc76479b9aff0a329b40235391eb24aec68d5692a
|
3 |
+
size 6486
|
runs/Sep28_15-46-58_ip-10-192-36-160/events.out.tfevents.1727538466.ip-10-192-36-160.3396001.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:129342c55cac974286c1e49598132d9778ac70c8e2a91fa76466651ba73a96c2
|
3 |
+
size 6907
|
runs/Sep28_15-48-28_ip-10-192-36-160/events.out.tfevents.1727538556.ip-10-192-36-160.3397127.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09633ff5fd32f4c3bfeba53817aab93730a6eb40d6421c813d3b0d7b24fb9318
|
3 |
+
size 6907
|
runs/Sep28_15-49-51_ip-10-192-36-160/events.out.tfevents.1727538639.ip-10-192-36-160.3398194.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7053a99485b2c384cf3b8353b6324227605710ce63472177f00186fce886aaf4
|
3 |
+
size 11311
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
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": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false,
|
43 |
+
"use_fast": true
|
44 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c107ded2345a05fa642d7df30d1a8dbe7f5196fc1e999e3d5a597ebb6c65a224
|
3 |
+
size 6200
|