Training in progress, step 500
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +2 -2
- runs/Jul15_10-23-45_ml-cluster/events.out.tfevents.1721039032.ml-cluster +3 -0
- runs/Jul15_10-26-34_ml-cluster/events.out.tfevents.1721039201.ml-cluster +3 -0
- special_tokens_map.json +21 -19
- tokenizer.json +1 -10
- tokenizer_config.json +5 -17
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"down_proj",
|
24 |
"gate_proj",
|
25 |
-
"q_proj",
|
26 |
"up_proj",
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"k_proj",
|
24 |
+
"o_proj",
|
25 |
"down_proj",
|
26 |
"gate_proj",
|
|
|
27 |
"up_proj",
|
28 |
+
"q_proj",
|
29 |
+
"v_proj"
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.safetensors
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 sha256:71f3095d5db5dc322b883b0f96815036247b716813a1978fbebb5812036a2a53
|
3 |
+
size 5544964896
|
runs/Jul15_10-23-45_ml-cluster/events.out.tfevents.1721039032.ml-cluster
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a84dd4805d73ae710c75fb2bcd2c67601b87a98e756635e7e2227db108f0178
|
3 |
+
size 5702
|
runs/Jul15_10-26-34_ml-cluster/events.out.tfevents.1721039201.ml-cluster
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd3661f9fcc70f9322b3aba80103d74deb5149462c6dddaa190a787e850fb4db
|
3 |
+
size 6267
|
special_tokens_map.json
CHANGED
@@ -1,21 +1,23 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
|
|
|
|
21 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
}
|
tokenizer.json
CHANGED
@@ -2314,16 +2314,7 @@
|
|
2314 |
},
|
2315 |
{
|
2316 |
"id": 128256,
|
2317 |
-
"content": "
|
2318 |
-
"single_word": false,
|
2319 |
-
"lstrip": false,
|
2320 |
-
"rstrip": false,
|
2321 |
-
"normalized": false,
|
2322 |
-
"special": true
|
2323 |
-
},
|
2324 |
-
{
|
2325 |
-
"id": 128257,
|
2326 |
-
"content": "<|im_end|>",
|
2327 |
"single_word": false,
|
2328 |
"lstrip": false,
|
2329 |
"rstrip": false,
|
|
|
2314 |
},
|
2315 |
{
|
2316 |
"id": 128256,
|
2317 |
+
"content": "<pad>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2318 |
"single_word": false,
|
2319 |
"lstrip": false,
|
2320 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -2049,15 +2049,7 @@
|
|
2049 |
"special": true
|
2050 |
},
|
2051 |
"128256": {
|
2052 |
-
"content": "
|
2053 |
-
"lstrip": false,
|
2054 |
-
"normalized": false,
|
2055 |
-
"rstrip": false,
|
2056 |
-
"single_word": false,
|
2057 |
-
"special": true
|
2058 |
-
},
|
2059 |
-
"128257": {
|
2060 |
-
"content": "<|im_end|>",
|
2061 |
"lstrip": false,
|
2062 |
"normalized": false,
|
2063 |
"rstrip": false,
|
@@ -2065,19 +2057,15 @@
|
|
2065 |
"special": true
|
2066 |
}
|
2067 |
},
|
2068 |
-
"
|
2069 |
-
|
2070 |
-
"<|im_end|>"
|
2071 |
-
],
|
2072 |
-
"bos_token": "<|im_start|>",
|
2073 |
-
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
2074 |
"clean_up_tokenization_spaces": true,
|
2075 |
-
"eos_token": "<|
|
2076 |
"model_input_names": [
|
2077 |
"input_ids",
|
2078 |
"attention_mask"
|
2079 |
],
|
2080 |
"model_max_length": 1000000000000000019884624838656,
|
2081 |
-
"pad_token": "
|
2082 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2083 |
}
|
|
|
2049 |
"special": true
|
2050 |
},
|
2051 |
"128256": {
|
2052 |
+
"content": "<pad>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2053 |
"lstrip": false,
|
2054 |
"normalized": false,
|
2055 |
"rstrip": false,
|
|
|
2057 |
"special": true
|
2058 |
}
|
2059 |
},
|
2060 |
+
"bos_token": "<|begin_of_text|>",
|
2061 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
|
|
|
|
|
|
|
|
2062 |
"clean_up_tokenization_spaces": true,
|
2063 |
+
"eos_token": "<|eot_id|>",
|
2064 |
"model_input_names": [
|
2065 |
"input_ids",
|
2066 |
"attention_mask"
|
2067 |
],
|
2068 |
"model_max_length": 1000000000000000019884624838656,
|
2069 |
+
"pad_token": "<pad>",
|
2070 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2071 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c7c45e99b74a411d83df194d282d22292c93328534a85f7a578272b2de2abd9
|
3 |
size 5432
|