Upload folder using huggingface_hub
Browse files- metadata.json +8 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +772 -0
- training_args.bin +3 -0
metadata.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"dataset_id": "tonyassi/sales1",
|
3 |
+
"value_column_name": "sales",
|
4 |
+
"test_split": 0.2,
|
5 |
+
"num_train_epochs": 10,
|
6 |
+
"learning_rate": 0.0001,
|
7 |
+
"max_value": 100000
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:903b0897d488d1d299e947416dab86a46c01d731ab2492e8d9933ede5b8ddd88
|
3 |
+
size 345583444
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3e816de489cc2ad3ef83315c80fae2e34d82f463fe569152f7a63d88975d3d3
|
3 |
+
size 686557178
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da1db5c227c2000e391e1d225e13a38eda71746be2164bab198c44af9ae0882b
|
3 |
+
size 13990
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c8eaa2a8b1b5ec96261497120f675979fe119748d8017a7cec0ad5b8bab9d4e
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,772 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 940,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.10638297872340426,
|
13 |
+
"grad_norm": 12.057719230651855,
|
14 |
+
"learning_rate": 9.893617021276596e-05,
|
15 |
+
"loss": 0.2856,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.2127659574468085,
|
20 |
+
"grad_norm": 9.51878547668457,
|
21 |
+
"learning_rate": 9.787234042553192e-05,
|
22 |
+
"loss": 0.1486,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.3191489361702128,
|
27 |
+
"grad_norm": 4.131153106689453,
|
28 |
+
"learning_rate": 9.680851063829788e-05,
|
29 |
+
"loss": 0.0795,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.425531914893617,
|
34 |
+
"grad_norm": 4.15078592300415,
|
35 |
+
"learning_rate": 9.574468085106384e-05,
|
36 |
+
"loss": 0.0634,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.5319148936170213,
|
41 |
+
"grad_norm": 6.101027011871338,
|
42 |
+
"learning_rate": 9.468085106382978e-05,
|
43 |
+
"loss": 0.0293,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.6382978723404256,
|
48 |
+
"grad_norm": 1.4290554523468018,
|
49 |
+
"learning_rate": 9.361702127659576e-05,
|
50 |
+
"loss": 0.02,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.7446808510638298,
|
55 |
+
"grad_norm": 0.2031591683626175,
|
56 |
+
"learning_rate": 9.25531914893617e-05,
|
57 |
+
"loss": 0.0084,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.851063829787234,
|
62 |
+
"grad_norm": 1.6767696142196655,
|
63 |
+
"learning_rate": 9.148936170212766e-05,
|
64 |
+
"loss": 0.0263,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.9574468085106383,
|
69 |
+
"grad_norm": 2.562359094619751,
|
70 |
+
"learning_rate": 9.042553191489363e-05,
|
71 |
+
"loss": 0.0095,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.0,
|
76 |
+
"eval_loss": 0.012819608673453331,
|
77 |
+
"eval_mse": 0.012819608673453331,
|
78 |
+
"eval_runtime": 13.8617,
|
79 |
+
"eval_samples_per_second": 13.49,
|
80 |
+
"eval_steps_per_second": 1.731,
|
81 |
+
"step": 94
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 1.0638297872340425,
|
85 |
+
"grad_norm": 4.054518222808838,
|
86 |
+
"learning_rate": 8.936170212765958e-05,
|
87 |
+
"loss": 0.0378,
|
88 |
+
"step": 100
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.1702127659574468,
|
92 |
+
"grad_norm": 1.0702558755874634,
|
93 |
+
"learning_rate": 8.829787234042553e-05,
|
94 |
+
"loss": 0.021,
|
95 |
+
"step": 110
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.2765957446808511,
|
99 |
+
"grad_norm": 3.5774471759796143,
|
100 |
+
"learning_rate": 8.723404255319149e-05,
|
101 |
+
"loss": 0.0087,
|
102 |
+
"step": 120
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 1.3829787234042552,
|
106 |
+
"grad_norm": 1.658952236175537,
|
107 |
+
"learning_rate": 8.617021276595745e-05,
|
108 |
+
"loss": 0.0188,
|
109 |
+
"step": 130
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 1.4893617021276595,
|
113 |
+
"grad_norm": 5.384657859802246,
|
114 |
+
"learning_rate": 8.510638297872341e-05,
|
115 |
+
"loss": 0.021,
|
116 |
+
"step": 140
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.5957446808510638,
|
120 |
+
"grad_norm": 6.726040840148926,
|
121 |
+
"learning_rate": 8.404255319148937e-05,
|
122 |
+
"loss": 0.0126,
|
123 |
+
"step": 150
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 1.702127659574468,
|
127 |
+
"grad_norm": 3.472024440765381,
|
128 |
+
"learning_rate": 8.297872340425533e-05,
|
129 |
+
"loss": 0.0069,
|
130 |
+
"step": 160
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 1.8085106382978724,
|
134 |
+
"grad_norm": 1.0799269676208496,
|
135 |
+
"learning_rate": 8.191489361702128e-05,
|
136 |
+
"loss": 0.0247,
|
137 |
+
"step": 170
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.9148936170212765,
|
141 |
+
"grad_norm": 2.496415138244629,
|
142 |
+
"learning_rate": 8.085106382978723e-05,
|
143 |
+
"loss": 0.0102,
|
144 |
+
"step": 180
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 2.0,
|
148 |
+
"eval_loss": 0.014377221465110779,
|
149 |
+
"eval_mse": 0.014377223327755928,
|
150 |
+
"eval_runtime": 13.5336,
|
151 |
+
"eval_samples_per_second": 13.817,
|
152 |
+
"eval_steps_per_second": 1.773,
|
153 |
+
"step": 188
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 2.021276595744681,
|
157 |
+
"grad_norm": 7.031186580657959,
|
158 |
+
"learning_rate": 7.978723404255319e-05,
|
159 |
+
"loss": 0.0146,
|
160 |
+
"step": 190
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 2.127659574468085,
|
164 |
+
"grad_norm": 1.6951093673706055,
|
165 |
+
"learning_rate": 7.872340425531916e-05,
|
166 |
+
"loss": 0.0102,
|
167 |
+
"step": 200
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 2.2340425531914896,
|
171 |
+
"grad_norm": 2.5294058322906494,
|
172 |
+
"learning_rate": 7.76595744680851e-05,
|
173 |
+
"loss": 0.0088,
|
174 |
+
"step": 210
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 2.3404255319148937,
|
178 |
+
"grad_norm": 0.2626056969165802,
|
179 |
+
"learning_rate": 7.659574468085106e-05,
|
180 |
+
"loss": 0.0089,
|
181 |
+
"step": 220
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 2.4468085106382977,
|
185 |
+
"grad_norm": 4.416263580322266,
|
186 |
+
"learning_rate": 7.553191489361703e-05,
|
187 |
+
"loss": 0.0211,
|
188 |
+
"step": 230
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.5531914893617023,
|
192 |
+
"grad_norm": 6.607398986816406,
|
193 |
+
"learning_rate": 7.446808510638298e-05,
|
194 |
+
"loss": 0.0114,
|
195 |
+
"step": 240
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 2.6595744680851063,
|
199 |
+
"grad_norm": 3.823686361312866,
|
200 |
+
"learning_rate": 7.340425531914894e-05,
|
201 |
+
"loss": 0.0113,
|
202 |
+
"step": 250
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 2.7659574468085104,
|
206 |
+
"grad_norm": 1.5682330131530762,
|
207 |
+
"learning_rate": 7.23404255319149e-05,
|
208 |
+
"loss": 0.0426,
|
209 |
+
"step": 260
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 2.872340425531915,
|
213 |
+
"grad_norm": 1.9752477407455444,
|
214 |
+
"learning_rate": 7.127659574468085e-05,
|
215 |
+
"loss": 0.0125,
|
216 |
+
"step": 270
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 2.978723404255319,
|
220 |
+
"grad_norm": 9.359685897827148,
|
221 |
+
"learning_rate": 7.021276595744681e-05,
|
222 |
+
"loss": 0.0293,
|
223 |
+
"step": 280
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 3.0,
|
227 |
+
"eval_loss": 0.008672923780977726,
|
228 |
+
"eval_mse": 0.008672923780977726,
|
229 |
+
"eval_runtime": 13.6388,
|
230 |
+
"eval_samples_per_second": 13.711,
|
231 |
+
"eval_steps_per_second": 1.76,
|
232 |
+
"step": 282
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"epoch": 3.0851063829787235,
|
236 |
+
"grad_norm": 1.2124550342559814,
|
237 |
+
"learning_rate": 6.914893617021277e-05,
|
238 |
+
"loss": 0.0153,
|
239 |
+
"step": 290
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 3.1914893617021276,
|
243 |
+
"grad_norm": 1.8096394538879395,
|
244 |
+
"learning_rate": 6.808510638297873e-05,
|
245 |
+
"loss": 0.0041,
|
246 |
+
"step": 300
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 3.297872340425532,
|
250 |
+
"grad_norm": 0.448832631111145,
|
251 |
+
"learning_rate": 6.702127659574469e-05,
|
252 |
+
"loss": 0.0028,
|
253 |
+
"step": 310
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 3.404255319148936,
|
257 |
+
"grad_norm": 3.3972675800323486,
|
258 |
+
"learning_rate": 6.595744680851063e-05,
|
259 |
+
"loss": 0.0139,
|
260 |
+
"step": 320
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.5106382978723403,
|
264 |
+
"grad_norm": 0.708503246307373,
|
265 |
+
"learning_rate": 6.489361702127659e-05,
|
266 |
+
"loss": 0.0042,
|
267 |
+
"step": 330
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 3.617021276595745,
|
271 |
+
"grad_norm": 3.509138345718384,
|
272 |
+
"learning_rate": 6.382978723404256e-05,
|
273 |
+
"loss": 0.0101,
|
274 |
+
"step": 340
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 3.723404255319149,
|
278 |
+
"grad_norm": 0.675829291343689,
|
279 |
+
"learning_rate": 6.276595744680851e-05,
|
280 |
+
"loss": 0.0072,
|
281 |
+
"step": 350
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 3.829787234042553,
|
285 |
+
"grad_norm": 0.2924118936061859,
|
286 |
+
"learning_rate": 6.170212765957447e-05,
|
287 |
+
"loss": 0.0119,
|
288 |
+
"step": 360
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"epoch": 3.9361702127659575,
|
292 |
+
"grad_norm": 0.0973350778222084,
|
293 |
+
"learning_rate": 6.063829787234043e-05,
|
294 |
+
"loss": 0.0083,
|
295 |
+
"step": 370
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 4.0,
|
299 |
+
"eval_loss": 0.00898202694952488,
|
300 |
+
"eval_mse": 0.00898202694952488,
|
301 |
+
"eval_runtime": 13.7858,
|
302 |
+
"eval_samples_per_second": 13.565,
|
303 |
+
"eval_steps_per_second": 1.741,
|
304 |
+
"step": 376
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 4.042553191489362,
|
308 |
+
"grad_norm": 1.605879783630371,
|
309 |
+
"learning_rate": 5.9574468085106384e-05,
|
310 |
+
"loss": 0.0138,
|
311 |
+
"step": 380
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 4.148936170212766,
|
315 |
+
"grad_norm": 3.2707700729370117,
|
316 |
+
"learning_rate": 5.851063829787234e-05,
|
317 |
+
"loss": 0.0051,
|
318 |
+
"step": 390
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 4.25531914893617,
|
322 |
+
"grad_norm": 0.4065483510494232,
|
323 |
+
"learning_rate": 5.744680851063831e-05,
|
324 |
+
"loss": 0.0068,
|
325 |
+
"step": 400
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 4.361702127659575,
|
329 |
+
"grad_norm": 3.0976128578186035,
|
330 |
+
"learning_rate": 5.638297872340426e-05,
|
331 |
+
"loss": 0.0081,
|
332 |
+
"step": 410
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 4.468085106382979,
|
336 |
+
"grad_norm": 2.073216438293457,
|
337 |
+
"learning_rate": 5.531914893617022e-05,
|
338 |
+
"loss": 0.0036,
|
339 |
+
"step": 420
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 4.574468085106383,
|
343 |
+
"grad_norm": 2.3855879306793213,
|
344 |
+
"learning_rate": 5.425531914893617e-05,
|
345 |
+
"loss": 0.0184,
|
346 |
+
"step": 430
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 4.680851063829787,
|
350 |
+
"grad_norm": 0.987083911895752,
|
351 |
+
"learning_rate": 5.319148936170213e-05,
|
352 |
+
"loss": 0.0138,
|
353 |
+
"step": 440
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 4.787234042553192,
|
357 |
+
"grad_norm": 0.3904077410697937,
|
358 |
+
"learning_rate": 5.212765957446809e-05,
|
359 |
+
"loss": 0.0076,
|
360 |
+
"step": 450
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 4.8936170212765955,
|
364 |
+
"grad_norm": 0.7371108531951904,
|
365 |
+
"learning_rate": 5.1063829787234044e-05,
|
366 |
+
"loss": 0.0166,
|
367 |
+
"step": 460
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 5.0,
|
371 |
+
"grad_norm": 1.442456603050232,
|
372 |
+
"learning_rate": 5e-05,
|
373 |
+
"loss": 0.0048,
|
374 |
+
"step": 470
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 5.0,
|
378 |
+
"eval_loss": 0.009333298541605473,
|
379 |
+
"eval_mse": 0.009333296678960323,
|
380 |
+
"eval_runtime": 13.8783,
|
381 |
+
"eval_samples_per_second": 13.474,
|
382 |
+
"eval_steps_per_second": 1.729,
|
383 |
+
"step": 470
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 5.1063829787234045,
|
387 |
+
"grad_norm": 0.8383665084838867,
|
388 |
+
"learning_rate": 4.893617021276596e-05,
|
389 |
+
"loss": 0.0075,
|
390 |
+
"step": 480
|
391 |
+
},
|
392 |
+
{
|
393 |
+
"epoch": 5.212765957446808,
|
394 |
+
"grad_norm": 0.11954376846551895,
|
395 |
+
"learning_rate": 4.787234042553192e-05,
|
396 |
+
"loss": 0.002,
|
397 |
+
"step": 490
|
398 |
+
},
|
399 |
+
{
|
400 |
+
"epoch": 5.319148936170213,
|
401 |
+
"grad_norm": 0.9294746518135071,
|
402 |
+
"learning_rate": 4.680851063829788e-05,
|
403 |
+
"loss": 0.0019,
|
404 |
+
"step": 500
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 5.425531914893617,
|
408 |
+
"grad_norm": 0.790674090385437,
|
409 |
+
"learning_rate": 4.574468085106383e-05,
|
410 |
+
"loss": 0.0117,
|
411 |
+
"step": 510
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 5.531914893617021,
|
415 |
+
"grad_norm": 1.9565446376800537,
|
416 |
+
"learning_rate": 4.468085106382979e-05,
|
417 |
+
"loss": 0.0049,
|
418 |
+
"step": 520
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 5.638297872340425,
|
422 |
+
"grad_norm": 2.9001126289367676,
|
423 |
+
"learning_rate": 4.3617021276595746e-05,
|
424 |
+
"loss": 0.004,
|
425 |
+
"step": 530
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 5.74468085106383,
|
429 |
+
"grad_norm": 1.8480255603790283,
|
430 |
+
"learning_rate": 4.2553191489361704e-05,
|
431 |
+
"loss": 0.0041,
|
432 |
+
"step": 540
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 5.851063829787234,
|
436 |
+
"grad_norm": 3.5987026691436768,
|
437 |
+
"learning_rate": 4.148936170212766e-05,
|
438 |
+
"loss": 0.0052,
|
439 |
+
"step": 550
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 5.957446808510638,
|
443 |
+
"grad_norm": 0.5824787616729736,
|
444 |
+
"learning_rate": 4.0425531914893614e-05,
|
445 |
+
"loss": 0.0028,
|
446 |
+
"step": 560
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 6.0,
|
450 |
+
"eval_loss": 0.006746174301952124,
|
451 |
+
"eval_mse": 0.006746174301952124,
|
452 |
+
"eval_runtime": 13.3949,
|
453 |
+
"eval_samples_per_second": 13.961,
|
454 |
+
"eval_steps_per_second": 1.792,
|
455 |
+
"step": 564
|
456 |
+
},
|
457 |
+
{
|
458 |
+
"epoch": 6.0638297872340425,
|
459 |
+
"grad_norm": 0.4667282700538635,
|
460 |
+
"learning_rate": 3.936170212765958e-05,
|
461 |
+
"loss": 0.0021,
|
462 |
+
"step": 570
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 6.170212765957447,
|
466 |
+
"grad_norm": 1.5866947174072266,
|
467 |
+
"learning_rate": 3.829787234042553e-05,
|
468 |
+
"loss": 0.0047,
|
469 |
+
"step": 580
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 6.276595744680851,
|
473 |
+
"grad_norm": 0.9419589042663574,
|
474 |
+
"learning_rate": 3.723404255319149e-05,
|
475 |
+
"loss": 0.0018,
|
476 |
+
"step": 590
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 6.382978723404255,
|
480 |
+
"grad_norm": 0.300542950630188,
|
481 |
+
"learning_rate": 3.617021276595745e-05,
|
482 |
+
"loss": 0.0012,
|
483 |
+
"step": 600
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 6.48936170212766,
|
487 |
+
"grad_norm": 0.741326093673706,
|
488 |
+
"learning_rate": 3.5106382978723407e-05,
|
489 |
+
"loss": 0.0035,
|
490 |
+
"step": 610
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 6.595744680851064,
|
494 |
+
"grad_norm": 1.8038232326507568,
|
495 |
+
"learning_rate": 3.4042553191489365e-05,
|
496 |
+
"loss": 0.0033,
|
497 |
+
"step": 620
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 6.702127659574468,
|
501 |
+
"grad_norm": 0.41880735754966736,
|
502 |
+
"learning_rate": 3.2978723404255317e-05,
|
503 |
+
"loss": 0.0048,
|
504 |
+
"step": 630
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 6.808510638297872,
|
508 |
+
"grad_norm": 0.6254183650016785,
|
509 |
+
"learning_rate": 3.191489361702128e-05,
|
510 |
+
"loss": 0.0018,
|
511 |
+
"step": 640
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 6.914893617021277,
|
515 |
+
"grad_norm": 0.13702178001403809,
|
516 |
+
"learning_rate": 3.085106382978723e-05,
|
517 |
+
"loss": 0.004,
|
518 |
+
"step": 650
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 7.0,
|
522 |
+
"eval_loss": 0.006701626814901829,
|
523 |
+
"eval_mse": 0.006701626814901829,
|
524 |
+
"eval_runtime": 13.4218,
|
525 |
+
"eval_samples_per_second": 13.933,
|
526 |
+
"eval_steps_per_second": 1.788,
|
527 |
+
"step": 658
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 7.0212765957446805,
|
531 |
+
"grad_norm": 0.8846572637557983,
|
532 |
+
"learning_rate": 2.9787234042553192e-05,
|
533 |
+
"loss": 0.0018,
|
534 |
+
"step": 660
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 7.127659574468085,
|
538 |
+
"grad_norm": 1.0834753513336182,
|
539 |
+
"learning_rate": 2.8723404255319154e-05,
|
540 |
+
"loss": 0.0007,
|
541 |
+
"step": 670
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 7.23404255319149,
|
545 |
+
"grad_norm": 0.28342002630233765,
|
546 |
+
"learning_rate": 2.765957446808511e-05,
|
547 |
+
"loss": 0.0026,
|
548 |
+
"step": 680
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 7.340425531914893,
|
552 |
+
"grad_norm": 0.33790862560272217,
|
553 |
+
"learning_rate": 2.6595744680851064e-05,
|
554 |
+
"loss": 0.0017,
|
555 |
+
"step": 690
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 7.446808510638298,
|
559 |
+
"grad_norm": 1.4947048425674438,
|
560 |
+
"learning_rate": 2.5531914893617022e-05,
|
561 |
+
"loss": 0.0023,
|
562 |
+
"step": 700
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 7.553191489361702,
|
566 |
+
"grad_norm": 1.0011037588119507,
|
567 |
+
"learning_rate": 2.446808510638298e-05,
|
568 |
+
"loss": 0.0014,
|
569 |
+
"step": 710
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 7.659574468085106,
|
573 |
+
"grad_norm": 0.686026930809021,
|
574 |
+
"learning_rate": 2.340425531914894e-05,
|
575 |
+
"loss": 0.0008,
|
576 |
+
"step": 720
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 7.76595744680851,
|
580 |
+
"grad_norm": 0.06300849467515945,
|
581 |
+
"learning_rate": 2.2340425531914894e-05,
|
582 |
+
"loss": 0.0016,
|
583 |
+
"step": 730
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 7.872340425531915,
|
587 |
+
"grad_norm": 0.5408380627632141,
|
588 |
+
"learning_rate": 2.1276595744680852e-05,
|
589 |
+
"loss": 0.0008,
|
590 |
+
"step": 740
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 7.9787234042553195,
|
594 |
+
"grad_norm": 0.07452932745218277,
|
595 |
+
"learning_rate": 2.0212765957446807e-05,
|
596 |
+
"loss": 0.0007,
|
597 |
+
"step": 750
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 8.0,
|
601 |
+
"eval_loss": 0.006444782949984074,
|
602 |
+
"eval_mse": 0.006444782949984074,
|
603 |
+
"eval_runtime": 13.594,
|
604 |
+
"eval_samples_per_second": 13.756,
|
605 |
+
"eval_steps_per_second": 1.765,
|
606 |
+
"step": 752
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 8.085106382978724,
|
610 |
+
"grad_norm": 0.5107563138008118,
|
611 |
+
"learning_rate": 1.9148936170212766e-05,
|
612 |
+
"loss": 0.0003,
|
613 |
+
"step": 760
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 8.191489361702128,
|
617 |
+
"grad_norm": 0.2516929507255554,
|
618 |
+
"learning_rate": 1.8085106382978724e-05,
|
619 |
+
"loss": 0.0004,
|
620 |
+
"step": 770
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 8.297872340425531,
|
624 |
+
"grad_norm": 0.24071469902992249,
|
625 |
+
"learning_rate": 1.7021276595744682e-05,
|
626 |
+
"loss": 0.001,
|
627 |
+
"step": 780
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 8.404255319148936,
|
631 |
+
"grad_norm": 0.13089929521083832,
|
632 |
+
"learning_rate": 1.595744680851064e-05,
|
633 |
+
"loss": 0.0004,
|
634 |
+
"step": 790
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 8.51063829787234,
|
638 |
+
"grad_norm": 1.771623969078064,
|
639 |
+
"learning_rate": 1.4893617021276596e-05,
|
640 |
+
"loss": 0.0011,
|
641 |
+
"step": 800
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 8.617021276595745,
|
645 |
+
"grad_norm": 0.585198163986206,
|
646 |
+
"learning_rate": 1.3829787234042554e-05,
|
647 |
+
"loss": 0.0006,
|
648 |
+
"step": 810
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 8.72340425531915,
|
652 |
+
"grad_norm": 1.7595680952072144,
|
653 |
+
"learning_rate": 1.2765957446808511e-05,
|
654 |
+
"loss": 0.0011,
|
655 |
+
"step": 820
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 8.829787234042554,
|
659 |
+
"grad_norm": 0.2941080331802368,
|
660 |
+
"learning_rate": 1.170212765957447e-05,
|
661 |
+
"loss": 0.0003,
|
662 |
+
"step": 830
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 8.936170212765958,
|
666 |
+
"grad_norm": 1.3685917854309082,
|
667 |
+
"learning_rate": 1.0638297872340426e-05,
|
668 |
+
"loss": 0.0008,
|
669 |
+
"step": 840
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 9.0,
|
673 |
+
"eval_loss": 0.006674789357930422,
|
674 |
+
"eval_mse": 0.006674789357930422,
|
675 |
+
"eval_runtime": 13.6694,
|
676 |
+
"eval_samples_per_second": 13.68,
|
677 |
+
"eval_steps_per_second": 1.756,
|
678 |
+
"step": 846
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 9.042553191489361,
|
682 |
+
"grad_norm": 0.4333817660808563,
|
683 |
+
"learning_rate": 9.574468085106383e-06,
|
684 |
+
"loss": 0.0004,
|
685 |
+
"step": 850
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 9.148936170212766,
|
689 |
+
"grad_norm": 0.21346421539783478,
|
690 |
+
"learning_rate": 8.510638297872341e-06,
|
691 |
+
"loss": 0.0002,
|
692 |
+
"step": 860
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 9.25531914893617,
|
696 |
+
"grad_norm": 0.13360550999641418,
|
697 |
+
"learning_rate": 7.446808510638298e-06,
|
698 |
+
"loss": 0.0002,
|
699 |
+
"step": 870
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 9.361702127659575,
|
703 |
+
"grad_norm": 0.20817670226097107,
|
704 |
+
"learning_rate": 6.3829787234042555e-06,
|
705 |
+
"loss": 0.0003,
|
706 |
+
"step": 880
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 9.46808510638298,
|
710 |
+
"grad_norm": 0.19471751153469086,
|
711 |
+
"learning_rate": 5.319148936170213e-06,
|
712 |
+
"loss": 0.0004,
|
713 |
+
"step": 890
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 9.574468085106384,
|
717 |
+
"grad_norm": 0.11478572338819504,
|
718 |
+
"learning_rate": 4.255319148936171e-06,
|
719 |
+
"loss": 0.0001,
|
720 |
+
"step": 900
|
721 |
+
},
|
722 |
+
{
|
723 |
+
"epoch": 9.680851063829786,
|
724 |
+
"grad_norm": 0.46695956587791443,
|
725 |
+
"learning_rate": 3.1914893617021277e-06,
|
726 |
+
"loss": 0.0003,
|
727 |
+
"step": 910
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 9.787234042553191,
|
731 |
+
"grad_norm": 0.15428566932678223,
|
732 |
+
"learning_rate": 2.1276595744680853e-06,
|
733 |
+
"loss": 0.0016,
|
734 |
+
"step": 920
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 9.893617021276595,
|
738 |
+
"grad_norm": 0.1379678100347519,
|
739 |
+
"learning_rate": 1.0638297872340427e-06,
|
740 |
+
"loss": 0.0001,
|
741 |
+
"step": 930
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 10.0,
|
745 |
+
"grad_norm": 0.21880577504634857,
|
746 |
+
"learning_rate": 0.0,
|
747 |
+
"loss": 0.0002,
|
748 |
+
"step": 940
|
749 |
+
}
|
750 |
+
],
|
751 |
+
"logging_steps": 10,
|
752 |
+
"max_steps": 940,
|
753 |
+
"num_input_tokens_seen": 0,
|
754 |
+
"num_train_epochs": 10,
|
755 |
+
"save_steps": 10,
|
756 |
+
"stateful_callbacks": {
|
757 |
+
"TrainerControl": {
|
758 |
+
"args": {
|
759 |
+
"should_epoch_stop": false,
|
760 |
+
"should_evaluate": false,
|
761 |
+
"should_log": false,
|
762 |
+
"should_save": true,
|
763 |
+
"should_training_stop": true
|
764 |
+
},
|
765 |
+
"attributes": {}
|
766 |
+
}
|
767 |
+
},
|
768 |
+
"total_flos": 0.0,
|
769 |
+
"train_batch_size": 8,
|
770 |
+
"trial_name": null,
|
771 |
+
"trial_params": null
|
772 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d41d379a4931fb56b83e75e6d129a7525b01ee48e3edc697145a3dc06f7b87cb
|
3 |
+
size 5048
|