Upload folder using huggingface_hub
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- special_tokens_map.json +1 -1
- tokenizer.json +9 -0
- tokenizer_config.json +9 -1
- trainer_state.json +25 -25
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -19,10 +19,10 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"dense_4h_to_h",
|
23 |
-
"dense_h_to_4h",
|
24 |
"query_key_value",
|
25 |
-
"dense"
|
|
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
22 |
"query_key_value",
|
23 |
+
"dense",
|
24 |
+
"dense_h_to_4h",
|
25 |
+
"dense_4h_to_h"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
28 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 134235712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74d3c94430da216e49b2f1edfd4d47a96775b1caf13c23787dde2966ddb28ff6
|
3 |
size 134235712
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268514874
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db0cfcb41260dc3ac3f0d2d7b951d685f8708331d34c01bad2d150ab37755fec
|
3 |
size 268514874
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8400da4ebd11656aee565d96885e25350dc287eec4ad76194986bfeef69bcc7
|
3 |
size 14244
|
special_tokens_map.json
CHANGED
@@ -30,7 +30,7 @@
|
|
30 |
"single_word": false
|
31 |
},
|
32 |
"pad_token": {
|
33 |
-
"content": "
|
34 |
"lstrip": false,
|
35 |
"normalized": false,
|
36 |
"rstrip": false,
|
|
|
30 |
"single_word": false
|
31 |
},
|
32 |
"pad_token": {
|
33 |
+
"content": "[PAD]",
|
34 |
"lstrip": false,
|
35 |
"normalized": false,
|
36 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -250,6 +250,15 @@
|
|
250 |
"rstrip": false,
|
251 |
"normalized": false,
|
252 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
253 |
}
|
254 |
],
|
255 |
"normalizer": {
|
|
|
250 |
"rstrip": false,
|
251 |
"normalized": false,
|
252 |
"special": true
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"id": 50279,
|
256 |
+
"content": "[PAD]",
|
257 |
+
"single_word": false,
|
258 |
+
"lstrip": false,
|
259 |
+
"rstrip": false,
|
260 |
+
"normalized": false,
|
261 |
+
"special": true
|
262 |
}
|
263 |
],
|
264 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -216,6 +216,14 @@
|
|
216 |
"rstrip": false,
|
217 |
"single_word": false,
|
218 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
219 |
}
|
220 |
},
|
221 |
"additional_special_tokens": [
|
@@ -226,7 +234,7 @@
|
|
226 |
"clean_up_tokenization_spaces": true,
|
227 |
"eos_token": "<|endoftext|>",
|
228 |
"model_max_length": 1000000000000000019884624838656,
|
229 |
-
"pad_token": "
|
230 |
"tokenizer_class": "GPTNeoXTokenizer",
|
231 |
"unk_token": "<|endoftext|>"
|
232 |
}
|
|
|
216 |
"rstrip": false,
|
217 |
"single_word": false,
|
218 |
"special": true
|
219 |
+
},
|
220 |
+
"50279": {
|
221 |
+
"content": "[PAD]",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
}
|
228 |
},
|
229 |
"additional_special_tokens": [
|
|
|
234 |
"clean_up_tokenization_spaces": true,
|
235 |
"eos_token": "<|endoftext|>",
|
236 |
"model_max_length": 1000000000000000019884624838656,
|
237 |
+
"pad_token": "[PAD]",
|
238 |
"tokenizer_class": "GPTNeoXTokenizer",
|
239 |
"unk_token": "<|endoftext|>"
|
240 |
}
|
trainer_state.json
CHANGED
@@ -11,145 +11,145 @@
|
|
11 |
{
|
12 |
"epoch": 0.04,
|
13 |
"learning_rate": 0.0002,
|
14 |
-
"loss": 2.
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.08,
|
19 |
"learning_rate": 0.0002,
|
20 |
-
"loss": 2.
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.12,
|
25 |
"learning_rate": 0.0002,
|
26 |
-
"loss": 2.
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.16,
|
31 |
"learning_rate": 0.0002,
|
32 |
-
"loss": 2.
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.21,
|
37 |
"learning_rate": 0.0002,
|
38 |
-
"loss": 2.
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.25,
|
43 |
"learning_rate": 0.0002,
|
44 |
-
"loss": 3.
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.29,
|
49 |
"learning_rate": 0.0002,
|
50 |
-
"loss": 2.
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.33,
|
55 |
"learning_rate": 0.0002,
|
56 |
-
"loss": 2.
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.37,
|
61 |
"learning_rate": 0.0002,
|
62 |
-
"loss": 2.
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.41,
|
67 |
"learning_rate": 0.0002,
|
68 |
-
"loss": 2.
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.45,
|
73 |
"learning_rate": 0.0002,
|
74 |
-
"loss": 2.
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.49,
|
79 |
"learning_rate": 0.0002,
|
80 |
-
"loss": 3.
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.53,
|
85 |
"learning_rate": 0.0002,
|
86 |
-
"loss": 2.
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.57,
|
91 |
"learning_rate": 0.0002,
|
92 |
-
"loss": 2.
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.62,
|
97 |
"learning_rate": 0.0002,
|
98 |
-
"loss": 2.
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.66,
|
103 |
"learning_rate": 0.0002,
|
104 |
-
"loss": 2.
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.7,
|
109 |
"learning_rate": 0.0002,
|
110 |
-
"loss": 2.
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.74,
|
115 |
"learning_rate": 0.0002,
|
116 |
-
"loss": 2.
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.78,
|
121 |
"learning_rate": 0.0002,
|
122 |
-
"loss": 2.
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.82,
|
127 |
"learning_rate": 0.0002,
|
128 |
-
"loss": 2.
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.86,
|
133 |
"learning_rate": 0.0002,
|
134 |
-
"loss": 2.
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.9,
|
139 |
"learning_rate": 0.0002,
|
140 |
-
"loss": 2.
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.94,
|
145 |
"learning_rate": 0.0002,
|
146 |
-
"loss": 2.
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.98,
|
151 |
"learning_rate": 0.0002,
|
152 |
-
"loss": 2.
|
153 |
"step": 48
|
154 |
}
|
155 |
],
|
@@ -158,7 +158,7 @@
|
|
158 |
"num_input_tokens_seen": 0,
|
159 |
"num_train_epochs": 1,
|
160 |
"save_steps": 500,
|
161 |
-
"total_flos":
|
162 |
"train_batch_size": 1,
|
163 |
"trial_name": null,
|
164 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 0.04,
|
13 |
"learning_rate": 0.0002,
|
14 |
+
"loss": 2.3426,
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.08,
|
19 |
"learning_rate": 0.0002,
|
20 |
+
"loss": 2.3786,
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.12,
|
25 |
"learning_rate": 0.0002,
|
26 |
+
"loss": 2.6959,
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.16,
|
31 |
"learning_rate": 0.0002,
|
32 |
+
"loss": 2.792,
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.21,
|
37 |
"learning_rate": 0.0002,
|
38 |
+
"loss": 2.8302,
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.25,
|
43 |
"learning_rate": 0.0002,
|
44 |
+
"loss": 3.3717,
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.29,
|
49 |
"learning_rate": 0.0002,
|
50 |
+
"loss": 2.2267,
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.33,
|
55 |
"learning_rate": 0.0002,
|
56 |
+
"loss": 2.5093,
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.37,
|
61 |
"learning_rate": 0.0002,
|
62 |
+
"loss": 2.7368,
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.41,
|
67 |
"learning_rate": 0.0002,
|
68 |
+
"loss": 2.5378,
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.45,
|
73 |
"learning_rate": 0.0002,
|
74 |
+
"loss": 2.6,
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.49,
|
79 |
"learning_rate": 0.0002,
|
80 |
+
"loss": 3.0639,
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.53,
|
85 |
"learning_rate": 0.0002,
|
86 |
+
"loss": 2.1673,
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.57,
|
91 |
"learning_rate": 0.0002,
|
92 |
+
"loss": 2.4645,
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.62,
|
97 |
"learning_rate": 0.0002,
|
98 |
+
"loss": 2.4987,
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.66,
|
103 |
"learning_rate": 0.0002,
|
104 |
+
"loss": 2.3191,
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.7,
|
109 |
"learning_rate": 0.0002,
|
110 |
+
"loss": 2.7003,
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.74,
|
115 |
"learning_rate": 0.0002,
|
116 |
+
"loss": 2.8433,
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.78,
|
121 |
"learning_rate": 0.0002,
|
122 |
+
"loss": 2.2216,
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.82,
|
127 |
"learning_rate": 0.0002,
|
128 |
+
"loss": 2.346,
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.86,
|
133 |
"learning_rate": 0.0002,
|
134 |
+
"loss": 2.3354,
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.9,
|
139 |
"learning_rate": 0.0002,
|
140 |
+
"loss": 2.4828,
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.94,
|
145 |
"learning_rate": 0.0002,
|
146 |
+
"loss": 2.6882,
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.98,
|
151 |
"learning_rate": 0.0002,
|
152 |
+
"loss": 2.7263,
|
153 |
"step": 48
|
154 |
}
|
155 |
],
|
|
|
158 |
"num_input_tokens_seen": 0,
|
159 |
"num_train_epochs": 1,
|
160 |
"save_steps": 500,
|
161 |
+
"total_flos": 2061789415243776.0,
|
162 |
"train_batch_size": 1,
|
163 |
"trial_name": null,
|
164 |
"trial_params": null
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d2faca9fc2994cb010b4af1851a2b88208d18c68e81e002db967e23a8aae6e1
|
3 |
size 4728
|