Training in progress, step 5000, checkpoint
Browse files
checkpoint-5000/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1711848436
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a70f84c9a27da6cc89fe26b166bdba66f29922afb79230b7c8e51fd8d2ce8cd
|
3 |
size 1711848436
|
checkpoint-5000/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3424043887
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2e578e20febd7dc9c2a263b7e82a788da5535ab71c93205f5df485ed3ce671c
|
3 |
size 3424043887
|
checkpoint-5000/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c27ac0a3d2034dad91961bc669b5c2fb5e7494176f10a59582c9af8a52b7263
|
3 |
size 623
|
checkpoint-5000/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l37-l/checkpoint-5000",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 5000,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,158 +9,158 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 2.
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
-
"epoch": 0.
|
28 |
-
"grad_norm":
|
29 |
-
"learning_rate": 2.
|
30 |
-
"loss": 0.
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
-
"epoch": 0.
|
35 |
-
"eval_loss": 1.
|
36 |
-
"eval_runtime":
|
37 |
-
"eval_samples_per_second": 15.
|
38 |
-
"eval_steps_per_second": 1.
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
-
"epoch": 0.
|
43 |
-
"grad_norm":
|
44 |
-
"learning_rate": 2.
|
45 |
-
"loss": 0.
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
-
"epoch": 0.
|
50 |
-
"eval_loss": 0.
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second":
|
53 |
-
"eval_steps_per_second": 1.
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
-
"epoch": 0.
|
58 |
-
"grad_norm":
|
59 |
-
"learning_rate": 2.
|
60 |
-
"loss": 0.
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
-
"epoch": 0.
|
65 |
-
"eval_loss": 0.
|
66 |
-
"eval_runtime":
|
67 |
-
"eval_samples_per_second": 15.
|
68 |
-
"eval_steps_per_second": 1.
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
-
"epoch": 0.
|
73 |
-
"grad_norm":
|
74 |
-
"learning_rate": 2.
|
75 |
-
"loss": 0.
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
-
"epoch": 0.
|
80 |
-
"eval_loss": 0.
|
81 |
-
"eval_runtime":
|
82 |
-
"eval_samples_per_second": 15.
|
83 |
-
"eval_steps_per_second": 1.
|
84 |
"step": 2500
|
85 |
},
|
86 |
{
|
87 |
-
"epoch": 0.
|
88 |
-
"grad_norm":
|
89 |
-
"learning_rate": 2.
|
90 |
-
"loss": 0.
|
91 |
"step": 3000
|
92 |
},
|
93 |
{
|
94 |
-
"epoch": 0.
|
95 |
-
"eval_loss": 0.
|
96 |
-
"eval_runtime":
|
97 |
-
"eval_samples_per_second": 15.
|
98 |
-
"eval_steps_per_second": 1.
|
99 |
"step": 3000
|
100 |
},
|
101 |
{
|
102 |
-
"epoch": 0.
|
103 |
-
"grad_norm":
|
104 |
-
"learning_rate": 2.
|
105 |
-
"loss": 0.
|
106 |
"step": 3500
|
107 |
},
|
108 |
{
|
109 |
-
"epoch": 0.
|
110 |
-
"eval_loss": 0.
|
111 |
-
"eval_runtime":
|
112 |
-
"eval_samples_per_second": 15.
|
113 |
-
"eval_steps_per_second": 1.
|
114 |
"step": 3500
|
115 |
},
|
116 |
{
|
117 |
-
"epoch": 0.
|
118 |
-
"grad_norm":
|
119 |
-
"learning_rate": 2.
|
120 |
-
"loss": 0.
|
121 |
"step": 4000
|
122 |
},
|
123 |
{
|
124 |
-
"epoch": 0.
|
125 |
-
"eval_loss": 0.
|
126 |
-
"eval_runtime":
|
127 |
-
"eval_samples_per_second": 15.
|
128 |
-
"eval_steps_per_second": 1.
|
129 |
"step": 4000
|
130 |
},
|
131 |
{
|
132 |
-
"epoch": 0.
|
133 |
-
"grad_norm":
|
134 |
-
"learning_rate": 2.
|
135 |
-
"loss": 0.
|
136 |
"step": 4500
|
137 |
},
|
138 |
{
|
139 |
-
"epoch": 0.
|
140 |
-
"eval_loss": 0.
|
141 |
-
"eval_runtime":
|
142 |
-
"eval_samples_per_second":
|
143 |
-
"eval_steps_per_second":
|
144 |
"step": 4500
|
145 |
},
|
146 |
{
|
147 |
-
"epoch": 0.
|
148 |
-
"grad_norm": 0.
|
149 |
-
"learning_rate": 2.
|
150 |
-
"loss": 0.
|
151 |
"step": 5000
|
152 |
},
|
153 |
{
|
154 |
-
"epoch": 0.
|
155 |
-
"eval_loss": 0.
|
156 |
-
"eval_runtime":
|
157 |
-
"eval_samples_per_second": 15.
|
158 |
-
"eval_steps_per_second": 1.
|
159 |
"step": 5000
|
160 |
}
|
161 |
],
|
162 |
"logging_steps": 500,
|
163 |
-
"max_steps":
|
164 |
"num_input_tokens_seen": 0,
|
165 |
"num_train_epochs": 3,
|
166 |
"save_steps": 500,
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7788484692573547,
|
3 |
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l37-l/checkpoint-5000",
|
4 |
+
"epoch": 0.5628729032984352,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 5000,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.056287290329843524,
|
13 |
+
"grad_norm": 96.92656707763672,
|
14 |
+
"learning_rate": 2.9437127096701565e-07,
|
15 |
+
"loss": 0.3748,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.056287290329843524,
|
20 |
+
"eval_loss": 1.2226382493972778,
|
21 |
+
"eval_runtime": 131.2779,
|
22 |
+
"eval_samples_per_second": 15.037,
|
23 |
+
"eval_steps_per_second": 1.882,
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
+
"epoch": 0.11257458065968705,
|
28 |
+
"grad_norm": 402.31158447265625,
|
29 |
+
"learning_rate": 2.887425419340313e-07,
|
30 |
+
"loss": 0.3057,
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
+
"epoch": 0.11257458065968705,
|
35 |
+
"eval_loss": 1.0702259540557861,
|
36 |
+
"eval_runtime": 131.0109,
|
37 |
+
"eval_samples_per_second": 15.067,
|
38 |
+
"eval_steps_per_second": 1.885,
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
+
"epoch": 0.16886187098953057,
|
43 |
+
"grad_norm": 515.0911865234375,
|
44 |
+
"learning_rate": 2.831138129010469e-07,
|
45 |
+
"loss": 0.2239,
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
+
"epoch": 0.16886187098953057,
|
50 |
+
"eval_loss": 0.9957238435745239,
|
51 |
+
"eval_runtime": 134.8377,
|
52 |
+
"eval_samples_per_second": 14.64,
|
53 |
+
"eval_steps_per_second": 1.832,
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
+
"epoch": 0.2251491613193741,
|
58 |
+
"grad_norm": 3.1967105865478516,
|
59 |
+
"learning_rate": 2.774850838680626e-07,
|
60 |
+
"loss": 0.2229,
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
+
"epoch": 0.2251491613193741,
|
65 |
+
"eval_loss": 0.9504629373550415,
|
66 |
+
"eval_runtime": 129.0169,
|
67 |
+
"eval_samples_per_second": 15.3,
|
68 |
+
"eval_steps_per_second": 1.914,
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
+
"epoch": 0.2814364516492176,
|
73 |
+
"grad_norm": 276.22998046875,
|
74 |
+
"learning_rate": 2.718563548350782e-07,
|
75 |
+
"loss": 0.2098,
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
+
"epoch": 0.2814364516492176,
|
80 |
+
"eval_loss": 0.9006705284118652,
|
81 |
+
"eval_runtime": 129.1816,
|
82 |
+
"eval_samples_per_second": 15.281,
|
83 |
+
"eval_steps_per_second": 1.912,
|
84 |
"step": 2500
|
85 |
},
|
86 |
{
|
87 |
+
"epoch": 0.33772374197906113,
|
88 |
+
"grad_norm": 1105.317138671875,
|
89 |
+
"learning_rate": 2.6622762580209386e-07,
|
90 |
+
"loss": 0.1938,
|
91 |
"step": 3000
|
92 |
},
|
93 |
{
|
94 |
+
"epoch": 0.33772374197906113,
|
95 |
+
"eval_loss": 0.8782906532287598,
|
96 |
+
"eval_runtime": 128.6387,
|
97 |
+
"eval_samples_per_second": 15.345,
|
98 |
+
"eval_steps_per_second": 1.92,
|
99 |
"step": 3000
|
100 |
},
|
101 |
{
|
102 |
+
"epoch": 0.39401103230890466,
|
103 |
+
"grad_norm": 0.00043465400813147426,
|
104 |
+
"learning_rate": 2.605988967691095e-07,
|
105 |
+
"loss": 0.1688,
|
106 |
"step": 3500
|
107 |
},
|
108 |
{
|
109 |
+
"epoch": 0.39401103230890466,
|
110 |
+
"eval_loss": 0.8405746221542358,
|
111 |
+
"eval_runtime": 128.6989,
|
112 |
+
"eval_samples_per_second": 15.338,
|
113 |
+
"eval_steps_per_second": 1.919,
|
114 |
"step": 3500
|
115 |
},
|
116 |
{
|
117 |
+
"epoch": 0.4502983226387482,
|
118 |
+
"grad_norm": 0.027426382526755333,
|
119 |
+
"learning_rate": 2.549701677361252e-07,
|
120 |
+
"loss": 0.1457,
|
121 |
"step": 4000
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 0.4502983226387482,
|
125 |
+
"eval_loss": 0.813768208026886,
|
126 |
+
"eval_runtime": 128.7209,
|
127 |
+
"eval_samples_per_second": 15.336,
|
128 |
+
"eval_steps_per_second": 1.919,
|
129 |
"step": 4000
|
130 |
},
|
131 |
{
|
132 |
+
"epoch": 0.5065856129685917,
|
133 |
+
"grad_norm": 0.0012935090344399214,
|
134 |
+
"learning_rate": 2.4934143870314085e-07,
|
135 |
+
"loss": 0.179,
|
136 |
"step": 4500
|
137 |
},
|
138 |
{
|
139 |
+
"epoch": 0.5065856129685917,
|
140 |
+
"eval_loss": 0.7965527176856995,
|
141 |
+
"eval_runtime": 128.3969,
|
142 |
+
"eval_samples_per_second": 15.374,
|
143 |
+
"eval_steps_per_second": 1.924,
|
144 |
"step": 4500
|
145 |
},
|
146 |
{
|
147 |
+
"epoch": 0.5628729032984352,
|
148 |
+
"grad_norm": 0.0017458726651966572,
|
149 |
+
"learning_rate": 2.4371270967015646e-07,
|
150 |
+
"loss": 0.1224,
|
151 |
"step": 5000
|
152 |
},
|
153 |
{
|
154 |
+
"epoch": 0.5628729032984352,
|
155 |
+
"eval_loss": 0.7788484692573547,
|
156 |
+
"eval_runtime": 128.4939,
|
157 |
+
"eval_samples_per_second": 15.363,
|
158 |
+
"eval_steps_per_second": 1.922,
|
159 |
"step": 5000
|
160 |
}
|
161 |
],
|
162 |
"logging_steps": 500,
|
163 |
+
"max_steps": 26649,
|
164 |
"num_input_tokens_seen": 0,
|
165 |
"num_train_epochs": 3,
|
166 |
"save_steps": 500,
|
checkpoint-5000/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4847
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:074eb2b3aae1f3310fb0b27d83d259baa7ad74a32c8433c81af819e28558f6b0
|
3 |
size 4847
|