🍻 cheers
Browse files- README.md +6 -5
- all_results.json +9 -4
- eval_results.json +6 -6
- runs/Apr16_07-14-49_7b4e89625b83/events.out.tfevents.1713255623.7b4e89625b83.34.2 +3 -0
- train_results.json +4 -4
- trainer_state.json +118 -118
README.md
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-base-patch16-224-in21k
|
4 |
tags:
|
|
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
- imagefolder
|
@@ -14,7 +15,7 @@ model-index:
|
|
14 |
name: Image Classification
|
15 |
type: image-classification
|
16 |
dataset:
|
17 |
-
name:
|
18 |
type: imagefolder
|
19 |
config: default
|
20 |
split: train
|
@@ -22,7 +23,7 @@ model-index:
|
|
22 |
metrics:
|
23 |
- name: Accuracy
|
24 |
type: accuracy
|
25 |
-
value: 0.
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# Action_model
|
32 |
|
33 |
-
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
-
- Accuracy: 0.
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
2 |
license: apache-2.0
|
3 |
base_model: google/vit-base-patch16-224-in21k
|
4 |
tags:
|
5 |
+
- image-classification
|
6 |
- generated_from_trainer
|
7 |
datasets:
|
8 |
- imagefolder
|
|
|
15 |
name: Image Classification
|
16 |
type: image-classification
|
17 |
dataset:
|
18 |
+
name: action_class
|
19 |
type: imagefolder
|
20 |
config: default
|
21 |
split: train
|
|
|
23 |
metrics:
|
24 |
- name: Accuracy
|
25 |
type: accuracy
|
26 |
+
value: 0.7885714285714286
|
27 |
---
|
28 |
|
29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
# Action_model
|
33 |
|
34 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the action_class dataset.
|
35 |
It achieves the following results on the evaluation set:
|
36 |
+
- Loss: 0.6974
|
37 |
+
- Accuracy: 0.7886
|
38 |
|
39 |
## Model description
|
40 |
|
all_results.json
CHANGED
@@ -1,8 +1,13 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
|
|
|
|
|
|
|
|
|
|
3 |
"total_flos": 1.555375746295849e+18,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
+
"eval_accuracy": 0.7885714285714286,
|
4 |
+
"eval_loss": 0.6974296569824219,
|
5 |
+
"eval_runtime": 15.598,
|
6 |
+
"eval_samples_per_second": 67.316,
|
7 |
+
"eval_steps_per_second": 8.463,
|
8 |
"total_flos": 1.555375746295849e+18,
|
9 |
+
"train_loss": 0.33379530375170857,
|
10 |
+
"train_runtime": 590.5675,
|
11 |
+
"train_samples_per_second": 33.984,
|
12 |
+
"train_steps_per_second": 1.063
|
13 |
}
|
eval_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime": 15.
|
6 |
-
"eval_samples_per_second":
|
7 |
-
"eval_steps_per_second": 8.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 2.0,
|
3 |
+
"eval_accuracy": 0.7885714285714286,
|
4 |
+
"eval_loss": 0.6974296569824219,
|
5 |
+
"eval_runtime": 15.598,
|
6 |
+
"eval_samples_per_second": 67.316,
|
7 |
+
"eval_steps_per_second": 8.463
|
8 |
}
|
runs/Apr16_07-14-49_7b4e89625b83/events.out.tfevents.1713255623.7b4e89625b83.34.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1130ab17d2afd6f827305aafdeec78829b8251cf2b664b9ba7b1eb859f6f7aa
|
3 |
+
size 411
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"total_flos": 1.555375746295849e+18,
|
4 |
-
"train_loss": 0.
|
5 |
-
"train_runtime":
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
"epoch": 2.0,
|
3 |
"total_flos": 1.555375746295849e+18,
|
4 |
+
"train_loss": 0.33379530375170857,
|
5 |
+
"train_runtime": 590.5675,
|
6 |
+
"train_samples_per_second": 33.984,
|
7 |
+
"train_steps_per_second": 1.063
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "Action_model/checkpoint-
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 100,
|
6 |
"global_step": 628,
|
@@ -10,283 +10,283 @@
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.06,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 9.681528662420382e-05,
|
15 |
-
"loss":
|
16 |
"step": 20
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.13,
|
20 |
-
"grad_norm":
|
21 |
"learning_rate": 9.363057324840766e-05,
|
22 |
-
"loss":
|
23 |
"step": 40
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.19,
|
27 |
-
"grad_norm":
|
28 |
"learning_rate": 9.044585987261147e-05,
|
29 |
-
"loss":
|
30 |
"step": 60
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.25,
|
34 |
-
"grad_norm":
|
35 |
"learning_rate": 8.726114649681529e-05,
|
36 |
-
"loss":
|
37 |
"step": 80
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.32,
|
41 |
-
"grad_norm":
|
42 |
"learning_rate": 8.407643312101911e-05,
|
43 |
-
"loss":
|
44 |
"step": 100
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.32,
|
48 |
-
"eval_accuracy": 0.
|
49 |
-
"eval_loss":
|
50 |
-
"eval_runtime":
|
51 |
-
"eval_samples_per_second":
|
52 |
-
"eval_steps_per_second":
|
53 |
"step": 100
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.38,
|
57 |
-
"grad_norm":
|
58 |
"learning_rate": 8.089171974522294e-05,
|
59 |
-
"loss":
|
60 |
"step": 120
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.45,
|
64 |
-
"grad_norm":
|
65 |
-
"learning_rate": 7.
|
66 |
-
"loss": 0.
|
67 |
"step": 140
|
68 |
},
|
69 |
{
|
70 |
"epoch": 0.51,
|
71 |
-
"grad_norm": 2.
|
72 |
-
"learning_rate": 7.
|
73 |
-
"loss": 0.
|
74 |
"step": 160
|
75 |
},
|
76 |
{
|
77 |
"epoch": 0.57,
|
78 |
-
"grad_norm":
|
79 |
-
"learning_rate": 7.
|
80 |
-
"loss": 0.
|
81 |
"step": 180
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.64,
|
85 |
-
"grad_norm":
|
86 |
-
"learning_rate": 6.
|
87 |
-
"loss": 0.
|
88 |
"step": 200
|
89 |
},
|
90 |
{
|
91 |
"epoch": 0.64,
|
92 |
-
"eval_accuracy": 0.
|
93 |
-
"eval_loss": 0.
|
94 |
-
"eval_runtime": 14.
|
95 |
-
"eval_samples_per_second":
|
96 |
-
"eval_steps_per_second":
|
97 |
"step": 200
|
98 |
},
|
99 |
{
|
100 |
"epoch": 0.7,
|
101 |
-
"grad_norm":
|
102 |
"learning_rate": 6.512738853503185e-05,
|
103 |
-
"loss": 0.
|
104 |
"step": 220
|
105 |
},
|
106 |
{
|
107 |
"epoch": 0.76,
|
108 |
-
"grad_norm":
|
109 |
"learning_rate": 6.194267515923567e-05,
|
110 |
-
"loss": 0.
|
111 |
"step": 240
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.83,
|
115 |
-
"grad_norm":
|
116 |
"learning_rate": 5.87579617834395e-05,
|
117 |
-
"loss": 0.
|
118 |
"step": 260
|
119 |
},
|
120 |
{
|
121 |
"epoch": 0.89,
|
122 |
-
"grad_norm":
|
123 |
"learning_rate": 5.5573248407643317e-05,
|
124 |
-
"loss": 0.
|
125 |
"step": 280
|
126 |
},
|
127 |
{
|
128 |
"epoch": 0.96,
|
129 |
-
"grad_norm":
|
130 |
"learning_rate": 5.238853503184714e-05,
|
131 |
-
"loss": 0.
|
132 |
"step": 300
|
133 |
},
|
134 |
{
|
135 |
"epoch": 0.96,
|
136 |
-
"eval_accuracy": 0.
|
137 |
-
"eval_loss": 0.
|
138 |
-
"eval_runtime": 14.
|
139 |
-
"eval_samples_per_second": 71.
|
140 |
-
"eval_steps_per_second":
|
141 |
"step": 300
|
142 |
},
|
143 |
{
|
144 |
"epoch": 1.02,
|
145 |
-
"grad_norm":
|
146 |
-
"learning_rate": 4.
|
147 |
-
"loss": 0.
|
148 |
"step": 320
|
149 |
},
|
150 |
{
|
151 |
"epoch": 1.08,
|
152 |
-
"grad_norm": 4.
|
153 |
-
"learning_rate": 4.
|
154 |
-
"loss": 0.
|
155 |
"step": 340
|
156 |
},
|
157 |
{
|
158 |
"epoch": 1.15,
|
159 |
-
"grad_norm":
|
160 |
-
"learning_rate": 4.
|
161 |
-
"loss": 0.
|
162 |
"step": 360
|
163 |
},
|
164 |
{
|
165 |
"epoch": 1.21,
|
166 |
-
"grad_norm":
|
167 |
-
"learning_rate": 3.
|
168 |
-
"loss": 0.
|
169 |
"step": 380
|
170 |
},
|
171 |
{
|
172 |
"epoch": 1.27,
|
173 |
-
"grad_norm": 2.
|
174 |
-
"learning_rate": 3.
|
175 |
-
"loss": 0.
|
176 |
"step": 400
|
177 |
},
|
178 |
{
|
179 |
"epoch": 1.27,
|
180 |
-
"eval_accuracy": 0.
|
181 |
-
"eval_loss": 0.
|
182 |
-
"eval_runtime": 14.
|
183 |
-
"eval_samples_per_second": 71.
|
184 |
-
"eval_steps_per_second": 8.
|
185 |
"step": 400
|
186 |
},
|
187 |
{
|
188 |
"epoch": 1.34,
|
189 |
-
"grad_norm":
|
190 |
-
"learning_rate": 3.
|
191 |
-
"loss": 0.
|
192 |
"step": 420
|
193 |
},
|
194 |
{
|
195 |
"epoch": 1.4,
|
196 |
-
"grad_norm":
|
197 |
-
"learning_rate": 3.
|
198 |
-
"loss": 0.
|
199 |
"step": 440
|
200 |
},
|
201 |
{
|
202 |
"epoch": 1.46,
|
203 |
-
"grad_norm":
|
204 |
-
"learning_rate": 2.
|
205 |
-
"loss": 0.
|
206 |
"step": 460
|
207 |
},
|
208 |
{
|
209 |
"epoch": 1.53,
|
210 |
-
"grad_norm":
|
211 |
-
"learning_rate": 2.
|
212 |
-
"loss": 0.
|
213 |
"step": 480
|
214 |
},
|
215 |
{
|
216 |
"epoch": 1.59,
|
217 |
-
"grad_norm":
|
218 |
-
"learning_rate": 2.
|
219 |
-
"loss": 0.
|
220 |
"step": 500
|
221 |
},
|
222 |
{
|
223 |
"epoch": 1.59,
|
224 |
-
"eval_accuracy": 0.
|
225 |
-
"eval_loss": 0.
|
226 |
-
"eval_runtime": 14.
|
227 |
-
"eval_samples_per_second":
|
228 |
-
"eval_steps_per_second": 9.
|
229 |
"step": 500
|
230 |
},
|
231 |
{
|
232 |
"epoch": 1.66,
|
233 |
-
"grad_norm":
|
234 |
-
"learning_rate": 1.
|
235 |
-
"loss": 0.
|
236 |
"step": 520
|
237 |
},
|
238 |
{
|
239 |
"epoch": 1.72,
|
240 |
-
"grad_norm": 3.
|
241 |
-
"learning_rate": 1.
|
242 |
-
"loss": 0.
|
243 |
"step": 540
|
244 |
},
|
245 |
{
|
246 |
"epoch": 1.78,
|
247 |
-
"grad_norm":
|
248 |
-
"learning_rate": 1.
|
249 |
-
"loss": 0.
|
250 |
"step": 560
|
251 |
},
|
252 |
{
|
253 |
"epoch": 1.85,
|
254 |
-
"grad_norm": 3.
|
255 |
-
"learning_rate":
|
256 |
-
"loss": 0.
|
257 |
"step": 580
|
258 |
},
|
259 |
{
|
260 |
"epoch": 1.91,
|
261 |
-
"grad_norm":
|
262 |
-
"learning_rate": 4.
|
263 |
-
"loss": 0.
|
264 |
"step": 600
|
265 |
},
|
266 |
{
|
267 |
"epoch": 1.91,
|
268 |
-
"eval_accuracy": 0.
|
269 |
-
"eval_loss": 0.
|
270 |
-
"eval_runtime": 14.
|
271 |
-
"eval_samples_per_second":
|
272 |
-
"eval_steps_per_second": 9.
|
273 |
"step": 600
|
274 |
},
|
275 |
{
|
276 |
"epoch": 1.97,
|
277 |
-
"grad_norm":
|
278 |
-
"learning_rate": 1.
|
279 |
-
"loss": 0.
|
280 |
"step": 620
|
281 |
},
|
282 |
{
|
283 |
"epoch": 2.0,
|
284 |
"step": 628,
|
285 |
"total_flos": 1.555375746295849e+18,
|
286 |
-
"train_loss": 0.
|
287 |
-
"train_runtime":
|
288 |
-
"train_samples_per_second":
|
289 |
-
"train_steps_per_second":
|
290 |
}
|
291 |
],
|
292 |
"logging_steps": 20,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.6974296569824219,
|
3 |
+
"best_model_checkpoint": "Action_model/checkpoint-200",
|
4 |
"epoch": 2.0,
|
5 |
"eval_steps": 100,
|
6 |
"global_step": 628,
|
|
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 0.06,
|
13 |
+
"grad_norm": 4.470834732055664,
|
14 |
"learning_rate": 9.681528662420382e-05,
|
15 |
+
"loss": 0.4514,
|
16 |
"step": 20
|
17 |
},
|
18 |
{
|
19 |
"epoch": 0.13,
|
20 |
+
"grad_norm": 3.164530038833618,
|
21 |
"learning_rate": 9.363057324840766e-05,
|
22 |
+
"loss": 0.4578,
|
23 |
"step": 40
|
24 |
},
|
25 |
{
|
26 |
"epoch": 0.19,
|
27 |
+
"grad_norm": 5.622269630432129,
|
28 |
"learning_rate": 9.044585987261147e-05,
|
29 |
+
"loss": 0.3927,
|
30 |
"step": 60
|
31 |
},
|
32 |
{
|
33 |
"epoch": 0.25,
|
34 |
+
"grad_norm": 4.455988883972168,
|
35 |
"learning_rate": 8.726114649681529e-05,
|
36 |
+
"loss": 0.4274,
|
37 |
"step": 80
|
38 |
},
|
39 |
{
|
40 |
"epoch": 0.32,
|
41 |
+
"grad_norm": 4.014460563659668,
|
42 |
"learning_rate": 8.407643312101911e-05,
|
43 |
+
"loss": 0.4296,
|
44 |
"step": 100
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.32,
|
48 |
+
"eval_accuracy": 0.7447619047619047,
|
49 |
+
"eval_loss": 0.8158602118492126,
|
50 |
+
"eval_runtime": 15.7498,
|
51 |
+
"eval_samples_per_second": 66.668,
|
52 |
+
"eval_steps_per_second": 8.381,
|
53 |
"step": 100
|
54 |
},
|
55 |
{
|
56 |
"epoch": 0.38,
|
57 |
+
"grad_norm": 5.374497890472412,
|
58 |
"learning_rate": 8.089171974522294e-05,
|
59 |
+
"loss": 0.4462,
|
60 |
"step": 120
|
61 |
},
|
62 |
{
|
63 |
"epoch": 0.45,
|
64 |
+
"grad_norm": 5.2211833000183105,
|
65 |
+
"learning_rate": 7.786624203821657e-05,
|
66 |
+
"loss": 0.4788,
|
67 |
"step": 140
|
68 |
},
|
69 |
{
|
70 |
"epoch": 0.51,
|
71 |
+
"grad_norm": 2.162199020385742,
|
72 |
+
"learning_rate": 7.468152866242038e-05,
|
73 |
+
"loss": 0.3794,
|
74 |
"step": 160
|
75 |
},
|
76 |
{
|
77 |
"epoch": 0.57,
|
78 |
+
"grad_norm": 2.3695385456085205,
|
79 |
+
"learning_rate": 7.14968152866242e-05,
|
80 |
+
"loss": 0.3611,
|
81 |
"step": 180
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.64,
|
85 |
+
"grad_norm": 3.2987468242645264,
|
86 |
+
"learning_rate": 6.831210191082804e-05,
|
87 |
+
"loss": 0.4083,
|
88 |
"step": 200
|
89 |
},
|
90 |
{
|
91 |
"epoch": 0.64,
|
92 |
+
"eval_accuracy": 0.7885714285714286,
|
93 |
+
"eval_loss": 0.6974296569824219,
|
94 |
+
"eval_runtime": 14.5668,
|
95 |
+
"eval_samples_per_second": 72.082,
|
96 |
+
"eval_steps_per_second": 9.062,
|
97 |
"step": 200
|
98 |
},
|
99 |
{
|
100 |
"epoch": 0.7,
|
101 |
+
"grad_norm": 3.8996469974517822,
|
102 |
"learning_rate": 6.512738853503185e-05,
|
103 |
+
"loss": 0.4064,
|
104 |
"step": 220
|
105 |
},
|
106 |
{
|
107 |
"epoch": 0.76,
|
108 |
+
"grad_norm": 4.896476745605469,
|
109 |
"learning_rate": 6.194267515923567e-05,
|
110 |
+
"loss": 0.3512,
|
111 |
"step": 240
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.83,
|
115 |
+
"grad_norm": 5.791750907897949,
|
116 |
"learning_rate": 5.87579617834395e-05,
|
117 |
+
"loss": 0.411,
|
118 |
"step": 260
|
119 |
},
|
120 |
{
|
121 |
"epoch": 0.89,
|
122 |
+
"grad_norm": 4.586860179901123,
|
123 |
"learning_rate": 5.5573248407643317e-05,
|
124 |
+
"loss": 0.2974,
|
125 |
"step": 280
|
126 |
},
|
127 |
{
|
128 |
"epoch": 0.96,
|
129 |
+
"grad_norm": 4.982791423797607,
|
130 |
"learning_rate": 5.238853503184714e-05,
|
131 |
+
"loss": 0.3384,
|
132 |
"step": 300
|
133 |
},
|
134 |
{
|
135 |
"epoch": 0.96,
|
136 |
+
"eval_accuracy": 0.7371428571428571,
|
137 |
+
"eval_loss": 0.8742781281471252,
|
138 |
+
"eval_runtime": 14.7081,
|
139 |
+
"eval_samples_per_second": 71.389,
|
140 |
+
"eval_steps_per_second": 8.975,
|
141 |
"step": 300
|
142 |
},
|
143 |
{
|
144 |
"epoch": 1.02,
|
145 |
+
"grad_norm": 2.271329879760742,
|
146 |
+
"learning_rate": 4.920382165605096e-05,
|
147 |
+
"loss": 0.3209,
|
148 |
"step": 320
|
149 |
},
|
150 |
{
|
151 |
"epoch": 1.08,
|
152 |
+
"grad_norm": 4.398645401000977,
|
153 |
+
"learning_rate": 4.601910828025478e-05,
|
154 |
+
"loss": 0.2851,
|
155 |
"step": 340
|
156 |
},
|
157 |
{
|
158 |
"epoch": 1.15,
|
159 |
+
"grad_norm": 4.354762077331543,
|
160 |
+
"learning_rate": 4.2834394904458604e-05,
|
161 |
+
"loss": 0.3029,
|
162 |
"step": 360
|
163 |
},
|
164 |
{
|
165 |
"epoch": 1.21,
|
166 |
+
"grad_norm": 1.9630823135375977,
|
167 |
+
"learning_rate": 3.964968152866242e-05,
|
168 |
+
"loss": 0.2774,
|
169 |
"step": 380
|
170 |
},
|
171 |
{
|
172 |
"epoch": 1.27,
|
173 |
+
"grad_norm": 2.4799087047576904,
|
174 |
+
"learning_rate": 3.646496815286624e-05,
|
175 |
+
"loss": 0.2812,
|
176 |
"step": 400
|
177 |
},
|
178 |
{
|
179 |
"epoch": 1.27,
|
180 |
+
"eval_accuracy": 0.7676190476190476,
|
181 |
+
"eval_loss": 0.7738763689994812,
|
182 |
+
"eval_runtime": 14.6761,
|
183 |
+
"eval_samples_per_second": 71.545,
|
184 |
+
"eval_steps_per_second": 8.994,
|
185 |
"step": 400
|
186 |
},
|
187 |
{
|
188 |
"epoch": 1.34,
|
189 |
+
"grad_norm": 5.377834320068359,
|
190 |
+
"learning_rate": 3.328025477707007e-05,
|
191 |
+
"loss": 0.2768,
|
192 |
"step": 420
|
193 |
},
|
194 |
{
|
195 |
"epoch": 1.4,
|
196 |
+
"grad_norm": 4.753965854644775,
|
197 |
+
"learning_rate": 3.0095541401273885e-05,
|
198 |
+
"loss": 0.3242,
|
199 |
"step": 440
|
200 |
},
|
201 |
{
|
202 |
"epoch": 1.46,
|
203 |
+
"grad_norm": 4.039095401763916,
|
204 |
+
"learning_rate": 2.6910828025477707e-05,
|
205 |
+
"loss": 0.2168,
|
206 |
"step": 460
|
207 |
},
|
208 |
{
|
209 |
"epoch": 1.53,
|
210 |
+
"grad_norm": 3.443063497543335,
|
211 |
+
"learning_rate": 2.372611464968153e-05,
|
212 |
+
"loss": 0.2584,
|
213 |
"step": 480
|
214 |
},
|
215 |
{
|
216 |
"epoch": 1.59,
|
217 |
+
"grad_norm": 1.6640291213989258,
|
218 |
+
"learning_rate": 2.054140127388535e-05,
|
219 |
+
"loss": 0.251,
|
220 |
"step": 500
|
221 |
},
|
222 |
{
|
223 |
"epoch": 1.59,
|
224 |
+
"eval_accuracy": 0.7857142857142857,
|
225 |
+
"eval_loss": 0.7165716886520386,
|
226 |
+
"eval_runtime": 14.6301,
|
227 |
+
"eval_samples_per_second": 71.77,
|
228 |
+
"eval_steps_per_second": 9.022,
|
229 |
"step": 500
|
230 |
},
|
231 |
{
|
232 |
"epoch": 1.66,
|
233 |
+
"grad_norm": 3.264369487762451,
|
234 |
+
"learning_rate": 1.7356687898089173e-05,
|
235 |
+
"loss": 0.2804,
|
236 |
"step": 520
|
237 |
},
|
238 |
{
|
239 |
"epoch": 1.72,
|
240 |
+
"grad_norm": 3.547678232192993,
|
241 |
+
"learning_rate": 1.4171974522292993e-05,
|
242 |
+
"loss": 0.2737,
|
243 |
"step": 540
|
244 |
},
|
245 |
{
|
246 |
"epoch": 1.78,
|
247 |
+
"grad_norm": 5.212786674499512,
|
248 |
+
"learning_rate": 1.0987261146496815e-05,
|
249 |
+
"loss": 0.2503,
|
250 |
"step": 560
|
251 |
},
|
252 |
{
|
253 |
"epoch": 1.85,
|
254 |
+
"grad_norm": 3.4162983894348145,
|
255 |
+
"learning_rate": 7.802547770700637e-06,
|
256 |
+
"loss": 0.253,
|
257 |
"step": 580
|
258 |
},
|
259 |
{
|
260 |
"epoch": 1.91,
|
261 |
+
"grad_norm": 5.042104244232178,
|
262 |
+
"learning_rate": 4.6178343949044585e-06,
|
263 |
+
"loss": 0.2425,
|
264 |
"step": 600
|
265 |
},
|
266 |
{
|
267 |
"epoch": 1.91,
|
268 |
+
"eval_accuracy": 0.7742857142857142,
|
269 |
+
"eval_loss": 0.7691510915756226,
|
270 |
+
"eval_runtime": 14.587,
|
271 |
+
"eval_samples_per_second": 71.982,
|
272 |
+
"eval_steps_per_second": 9.049,
|
273 |
"step": 600
|
274 |
},
|
275 |
{
|
276 |
"epoch": 1.97,
|
277 |
+
"grad_norm": 5.002872467041016,
|
278 |
+
"learning_rate": 1.4331210191082802e-06,
|
279 |
+
"loss": 0.2493,
|
280 |
"step": 620
|
281 |
},
|
282 |
{
|
283 |
"epoch": 2.0,
|
284 |
"step": 628,
|
285 |
"total_flos": 1.555375746295849e+18,
|
286 |
+
"train_loss": 0.33379530375170857,
|
287 |
+
"train_runtime": 590.5675,
|
288 |
+
"train_samples_per_second": 33.984,
|
289 |
+
"train_steps_per_second": 1.063
|
290 |
}
|
291 |
],
|
292 |
"logging_steps": 20,
|