Training in progress, step 500
Browse files- adapter_config.json +4 -4
- adapter_model.safetensors +2 -2
- runs/Jul14_14-58-08_ml-cluster/events.out.tfevents.1720969092.ml-cluster +3 -0
- runs/Jul14_14-59-55_ml-cluster/events.out.tfevents.1720969199.ml-cluster +3 -0
- special_tokens_map.json +15 -19
- tokenizer.json +0 -18
- tokenizer_config.json +3 -24
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
23 |
"up_proj",
|
24 |
-
"
|
25 |
"o_proj",
|
26 |
-
"v_proj",
|
27 |
"k_proj",
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
"up_proj",
|
25 |
+
"q_proj",
|
26 |
"o_proj",
|
|
|
27 |
"k_proj",
|
28 |
+
"down_proj",
|
29 |
+
"gate_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 sha256:853b3e25a4f56a4058e2078c5744e4f1921ae8c9ef88fca3ca29050b836218f6
|
3 |
+
size 167832240
|
runs/Jul14_14-58-08_ml-cluster/events.out.tfevents.1720969092.ml-cluster
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39ee42f63209abe90cb8ebf75f1d51e43bff4b384d51899691ed380691ba4c5a
|
3 |
+
size 5702
|
runs/Jul14_14-59-55_ml-cluster/events.out.tfevents.1720969199.ml-cluster
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f4be315bf2ecfce060091693340341a56f61b00183d03eb0162c1fa7c6c9d94
|
3 |
+
size 5702
|
special_tokens_map.json
CHANGED
@@ -1,21 +1,17 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
],
|
18 |
-
"bos_token": "<|im_start|>",
|
19 |
-
"eos_token": "<|im_end|>",
|
20 |
-
"pad_token": "<|im_end|>"
|
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": "<|end_of_text|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|end_of_text|>"
|
|
|
|
|
|
|
|
|
17 |
}
|
tokenizer.json
CHANGED
@@ -2311,24 +2311,6 @@
|
|
2311 |
"rstrip": false,
|
2312 |
"normalized": false,
|
2313 |
"special": true
|
2314 |
-
},
|
2315 |
-
{
|
2316 |
-
"id": 128256,
|
2317 |
-
"content": "<|im_start|>",
|
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,
|
2330 |
-
"normalized": false,
|
2331 |
-
"special": true
|
2332 |
}
|
2333 |
],
|
2334 |
"normalizer": null,
|
|
|
2311 |
"rstrip": false,
|
2312 |
"normalized": false,
|
2313 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2314 |
}
|
2315 |
],
|
2316 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -2047,37 +2047,16 @@
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
2050 |
-
},
|
2051 |
-
"128256": {
|
2052 |
-
"content": "<|im_start|>",
|
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,
|
2064 |
-
"single_word": false,
|
2065 |
-
"special": true
|
2066 |
}
|
2067 |
},
|
2068 |
-
"
|
2069 |
-
"<|im_start|>",
|
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 |
}
|
|
|
2047 |
"rstrip": false,
|
2048 |
"single_word": false,
|
2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
|
|
|
|
|
|
|
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
+
"eos_token": "<|end_of_text|>",
|
2055 |
"model_input_names": [
|
2056 |
"input_ids",
|
2057 |
"attention_mask"
|
2058 |
],
|
2059 |
"model_max_length": 1000000000000000019884624838656,
|
2060 |
+
"pad_token": "<|end_of_text|>",
|
2061 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2062 |
}
|
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 sha256:1ecda7d7300bb607ef09690b066dcf6aa108dfb72fad4082997b8645b12578b6
|
3 |
size 5432
|