Training in progress, step 100
Browse files- config.json +26 -0
- runs/Apr19_11-55-07_n136-147-090/events.out.tfevents.1713501585.n136-147-090.252697.0 +3 -0
- runs/Apr19_12-56-05_n136-147-090/events.out.tfevents.1713502620.n136-147-090.291311.0 +3 -0
- runs/Apr19_13-01-36_n136-147-090/events.out.tfevents.1713502951.n136-147-090.293651.0 +3 -0
- runs/Apr19_13-03-46_n136-147-090/events.out.tfevents.1713503093.n136-147-090.295674.0 +3 -0
- runs/Apr19_13-53-20_n136-147-090/events.out.tfevents.1713507208.n136-147-090.314082.0 +3 -0
- runs/Apr19_14-12-55_n136-147-090/events.out.tfevents.1713507391.n136-147-090.335860.0 +3 -0
- runs/Apr19_14-16-26_n136-147-090/events.out.tfevents.1713507447.n136-147-090.343478.0 +3 -0
- runs/Apr19_14-21-06_n136-147-090/events.out.tfevents.1713508878.n136-147-090.348202.0 +3 -0
- runs/Apr19_15-16-27_n136-147-090/events.out.tfevents.1713511167.n136-147-090.391336.0 +3 -0
- runs/Apr19_15-20-27_n136-147-090/events.out.tfevents.1713511251.n136-147-090.395396.0 +3 -0
- runs/Apr19_15-26-54_n136-147-090/events.out.tfevents.1713511632.n136-147-090.400266.0 +3 -0
- runs/Apr19_15-43-13_n136-147-090/events.out.tfevents.1713512613.n136-147-090.408119.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
runs/Apr19_11-55-07_n136-147-090/events.out.tfevents.1713501585.n136-147-090.252697.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c24dea46d1e602cb3f1c8a27277bb31cf5053cee6a578fa389b2323b413b5c29
|
3 |
+
size 4697
|
runs/Apr19_12-56-05_n136-147-090/events.out.tfevents.1713502620.n136-147-090.291311.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac3df19e520fb461ced3f493c39485cb5c0a43764d6212a7f56419ff324fa936
|
3 |
+
size 4697
|
runs/Apr19_13-01-36_n136-147-090/events.out.tfevents.1713502951.n136-147-090.293651.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec11e66e4e6f7d6b5de9efbaa4f7bf53efb82a8365a3fdc08c3781adfb776149
|
3 |
+
size 4697
|
runs/Apr19_13-03-46_n136-147-090/events.out.tfevents.1713503093.n136-147-090.295674.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20df062c98ba958d0be1b62a460e76398283ecd37bd67a35b0aa57424274dd40
|
3 |
+
size 4697
|
runs/Apr19_13-53-20_n136-147-090/events.out.tfevents.1713507208.n136-147-090.314082.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dccdae4ea9e8f19908162683e7a11082bea163762c5a1dd6c169a5cc1986f75
|
3 |
+
size 4664
|
runs/Apr19_14-12-55_n136-147-090/events.out.tfevents.1713507391.n136-147-090.335860.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0507524644edacd3c28c308f78e24686eda160c781eb1fa970e8a17fc8b787e5
|
3 |
+
size 4664
|
runs/Apr19_14-16-26_n136-147-090/events.out.tfevents.1713507447.n136-147-090.343478.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a85a889560e9a16a135873b79cb2fda6da15cac5b47c073e0c572e1b97fda3e
|
3 |
+
size 4664
|
runs/Apr19_14-21-06_n136-147-090/events.out.tfevents.1713508878.n136-147-090.348202.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c3435cb9da8daf87b6601da7961da3a0d9a4f40c0cc2f01427caf70b27489f1
|
3 |
+
size 4664
|
runs/Apr19_15-16-27_n136-147-090/events.out.tfevents.1713511167.n136-147-090.391336.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2c5ca09535fb986cfc7ac7bb5d2624d675f5aa7205c980165b5e0e5858a60fc
|
3 |
+
size 4664
|
runs/Apr19_15-20-27_n136-147-090/events.out.tfevents.1713511251.n136-147-090.395396.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53daaf92b8c7583673e41aaac419c45b8b871ab84eca91b77c2f2cb0b41a4b74
|
3 |
+
size 4664
|
runs/Apr19_15-26-54_n136-147-090/events.out.tfevents.1713511632.n136-147-090.400266.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eca3d1d58727722445320f7d8e881b0396a2add61d9655a0b9045efa6bdd1fe6
|
3 |
+
size 4664
|
runs/Apr19_15-43-13_n136-147-090/events.out.tfevents.1713512613.n136-147-090.408119.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1f84c5c24fcd31a3117f36ed09cc0023c1e008d8ea70b6496a6ca5f6ae9a62c
|
3 |
+
size 9011
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a1a47f129a9c5ef9d01967ad69e7f3da2e377c46b21febbb75510e11224cc4d
|
3 |
+
size 6072
|