Upload folder using huggingface_hub
Browse files- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- trainer_state.json +34 -34
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -19,13 +19,13 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"k_proj",
|
24 |
"gate_proj",
|
|
|
|
|
25 |
"v_proj",
|
26 |
-
"
|
27 |
-
"o_proj"
|
28 |
-
"up_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"down_proj",
|
|
|
23 |
"gate_proj",
|
24 |
+
"k_proj",
|
25 |
+
"up_proj",
|
26 |
"v_proj",
|
27 |
+
"q_proj",
|
28 |
+
"o_proj"
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"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 242266152
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e25142d852c6940ad957a923e3fe68ca5f5f8b3ce880dee1752c4c41264d7ab4
|
3 |
size 242266152
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484650042
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b6be3cc008feeded06cde5e56a5bf99a1070589e2edbe0b4c69a7736d19099a
|
3 |
size 484650042
|
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:e33a6d44a2283d71de5c5a65eec778978acfc2025c73f1fc9173a25b45f34436
|
3 |
size 14244
|
trainer_state.json
CHANGED
@@ -11,199 +11,199 @@
|
|
11 |
{
|
12 |
"epoch": 0.03,
|
13 |
"learning_rate": 0.0002,
|
14 |
-
"loss": 2.
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.06,
|
19 |
"learning_rate": 0.0002,
|
20 |
-
"loss": 1.
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.09,
|
25 |
"learning_rate": 0.0002,
|
26 |
-
"loss": 1.
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.12,
|
31 |
"learning_rate": 0.0002,
|
32 |
-
"loss": 1.
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.15,
|
37 |
"learning_rate": 0.0002,
|
38 |
-
"loss": 1.
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.18,
|
43 |
"learning_rate": 0.0002,
|
44 |
-
"loss": 1.
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.21,
|
49 |
"learning_rate": 0.0002,
|
50 |
-
"loss": 1.
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.24,
|
55 |
"learning_rate": 0.0002,
|
56 |
-
"loss": 2.
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.27,
|
61 |
"learning_rate": 0.0002,
|
62 |
-
"loss": 2.
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.3,
|
67 |
"learning_rate": 0.0002,
|
68 |
-
"loss": 1.
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.33,
|
73 |
"learning_rate": 0.0002,
|
74 |
-
"loss": 1.
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.36,
|
79 |
"learning_rate": 0.0002,
|
80 |
-
"loss": 1.
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.39,
|
85 |
"learning_rate": 0.0002,
|
86 |
-
"loss": 1.
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.42,
|
91 |
"learning_rate": 0.0002,
|
92 |
-
"loss": 1.
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.45,
|
97 |
"learning_rate": 0.0002,
|
98 |
-
"loss": 1.
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.48,
|
103 |
"learning_rate": 0.0002,
|
104 |
-
"loss": 1.
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.51,
|
109 |
"learning_rate": 0.0002,
|
110 |
-
"loss":
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.54,
|
115 |
"learning_rate": 0.0002,
|
116 |
-
"loss": 1.
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.57,
|
121 |
"learning_rate": 0.0002,
|
122 |
-
"loss": 1.
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.6,
|
127 |
"learning_rate": 0.0002,
|
128 |
-
"loss": 1.
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.63,
|
133 |
"learning_rate": 0.0002,
|
134 |
-
"loss": 1.
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.66,
|
139 |
"learning_rate": 0.0002,
|
140 |
-
"loss": 1.
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.69,
|
145 |
"learning_rate": 0.0002,
|
146 |
-
"loss": 1.
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.72,
|
151 |
"learning_rate": 0.0002,
|
152 |
-
"loss": 1.
|
153 |
"step": 48
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.75,
|
157 |
"learning_rate": 0.0002,
|
158 |
-
"loss": 2.
|
159 |
"step": 50
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.78,
|
163 |
"learning_rate": 0.0002,
|
164 |
-
"loss": 1.
|
165 |
"step": 52
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.81,
|
169 |
"learning_rate": 0.0002,
|
170 |
-
"loss": 1.
|
171 |
"step": 54
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.84,
|
175 |
"learning_rate": 0.0002,
|
176 |
-
"loss": 1.
|
177 |
"step": 56
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.86,
|
181 |
"learning_rate": 0.0002,
|
182 |
-
"loss": 1.
|
183 |
"step": 58
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.89,
|
187 |
"learning_rate": 0.0002,
|
188 |
-
"loss": 1.
|
189 |
"step": 60
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.92,
|
193 |
"learning_rate": 0.0002,
|
194 |
-
"loss": 1.
|
195 |
"step": 62
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.95,
|
199 |
"learning_rate": 0.0002,
|
200 |
-
"loss": 1.
|
201 |
"step": 64
|
202 |
},
|
203 |
{
|
204 |
"epoch": 0.98,
|
205 |
"learning_rate": 0.0002,
|
206 |
-
"loss": 1.
|
207 |
"step": 66
|
208 |
}
|
209 |
],
|
@@ -212,7 +212,7 @@
|
|
212 |
"num_input_tokens_seen": 0,
|
213 |
"num_train_epochs": 1,
|
214 |
"save_steps": 500,
|
215 |
-
"total_flos":
|
216 |
"train_batch_size": 1,
|
217 |
"trial_name": null,
|
218 |
"trial_params": null
|
|
|
11 |
{
|
12 |
"epoch": 0.03,
|
13 |
"learning_rate": 0.0002,
|
14 |
+
"loss": 2.7359,
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.06,
|
19 |
"learning_rate": 0.0002,
|
20 |
+
"loss": 1.7382,
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.09,
|
25 |
"learning_rate": 0.0002,
|
26 |
+
"loss": 1.5779,
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.12,
|
31 |
"learning_rate": 0.0002,
|
32 |
+
"loss": 1.4905,
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.15,
|
37 |
"learning_rate": 0.0002,
|
38 |
+
"loss": 1.3959,
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.18,
|
43 |
"learning_rate": 0.0002,
|
44 |
+
"loss": 1.5667,
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.21,
|
49 |
"learning_rate": 0.0002,
|
50 |
+
"loss": 1.7249,
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.24,
|
55 |
"learning_rate": 0.0002,
|
56 |
+
"loss": 2.2016,
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.27,
|
61 |
"learning_rate": 0.0002,
|
62 |
+
"loss": 2.2788,
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.3,
|
67 |
"learning_rate": 0.0002,
|
68 |
+
"loss": 1.7629,
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.33,
|
73 |
"learning_rate": 0.0002,
|
74 |
+
"loss": 1.414,
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.36,
|
79 |
"learning_rate": 0.0002,
|
80 |
+
"loss": 1.3766,
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.39,
|
85 |
"learning_rate": 0.0002,
|
86 |
+
"loss": 1.2258,
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.42,
|
91 |
"learning_rate": 0.0002,
|
92 |
+
"loss": 1.3666,
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.45,
|
97 |
"learning_rate": 0.0002,
|
98 |
+
"loss": 1.5935,
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.48,
|
103 |
"learning_rate": 0.0002,
|
104 |
+
"loss": 1.5005,
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.51,
|
109 |
"learning_rate": 0.0002,
|
110 |
+
"loss": 1.9383,
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.54,
|
115 |
"learning_rate": 0.0002,
|
116 |
+
"loss": 1.5443,
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.57,
|
121 |
"learning_rate": 0.0002,
|
122 |
+
"loss": 1.4088,
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.6,
|
127 |
"learning_rate": 0.0002,
|
128 |
+
"loss": 1.4293,
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.63,
|
133 |
"learning_rate": 0.0002,
|
134 |
+
"loss": 1.1608,
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.66,
|
139 |
"learning_rate": 0.0002,
|
140 |
+
"loss": 1.2382,
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.69,
|
145 |
"learning_rate": 0.0002,
|
146 |
+
"loss": 1.4817,
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.72,
|
151 |
"learning_rate": 0.0002,
|
152 |
+
"loss": 1.5242,
|
153 |
"step": 48
|
154 |
},
|
155 |
{
|
156 |
"epoch": 0.75,
|
157 |
"learning_rate": 0.0002,
|
158 |
+
"loss": 2.5209,
|
159 |
"step": 50
|
160 |
},
|
161 |
{
|
162 |
"epoch": 0.78,
|
163 |
"learning_rate": 0.0002,
|
164 |
+
"loss": 1.346,
|
165 |
"step": 52
|
166 |
},
|
167 |
{
|
168 |
"epoch": 0.81,
|
169 |
"learning_rate": 0.0002,
|
170 |
+
"loss": 1.5437,
|
171 |
"step": 54
|
172 |
},
|
173 |
{
|
174 |
"epoch": 0.84,
|
175 |
"learning_rate": 0.0002,
|
176 |
+
"loss": 1.4825,
|
177 |
"step": 56
|
178 |
},
|
179 |
{
|
180 |
"epoch": 0.86,
|
181 |
"learning_rate": 0.0002,
|
182 |
+
"loss": 1.1331,
|
183 |
"step": 58
|
184 |
},
|
185 |
{
|
186 |
"epoch": 0.89,
|
187 |
"learning_rate": 0.0002,
|
188 |
+
"loss": 1.3705,
|
189 |
"step": 60
|
190 |
},
|
191 |
{
|
192 |
"epoch": 0.92,
|
193 |
"learning_rate": 0.0002,
|
194 |
+
"loss": 1.4236,
|
195 |
"step": 62
|
196 |
},
|
197 |
{
|
198 |
"epoch": 0.95,
|
199 |
"learning_rate": 0.0002,
|
200 |
+
"loss": 1.4443,
|
201 |
"step": 64
|
202 |
},
|
203 |
{
|
204 |
"epoch": 0.98,
|
205 |
"learning_rate": 0.0002,
|
206 |
+
"loss": 1.6586,
|
207 |
"step": 66
|
208 |
}
|
209 |
],
|
|
|
212 |
"num_input_tokens_seen": 0,
|
213 |
"num_train_epochs": 1,
|
214 |
"save_steps": 500,
|
215 |
+
"total_flos": 4514520321982464.0,
|
216 |
"train_batch_size": 1,
|
217 |
"trial_name": null,
|
218 |
"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:ccbbef329ba894e258c57aa7b70826f7d56a2abde99647c6fe9d6743de3ffefe
|
3 |
size 4728
|