Training in progress, step 4500, checkpoint
Browse files
checkpoint-4500/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:c913361aa159377d3d737d35196b0e48eda3669d2a4d41a478d15e5527ac4afa
|
3 |
size 1711848436
|
checkpoint-4500/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:c4dbfb4c3027aaa2ce519641b38d02032b2e32c2525750fa5d68cad5dadce52f
|
3 |
size 3424043887
|
checkpoint-4500/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 sha256:510f35f120a516dc8542b9fd7f1dbea2ac61d60efde7590c4fba85afd28ba517
|
3 |
size 623
|
checkpoint-4500/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 4500,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,145 +9,145 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 4.
|
15 |
-
"loss": 0.
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"eval_loss": 1.
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second": 15.
|
23 |
-
"eval_steps_per_second": 1.
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
-
"epoch": 0.
|
28 |
-
"grad_norm":
|
29 |
-
"learning_rate": 4.
|
30 |
-
"loss": 0.
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
-
"epoch": 0.
|
35 |
-
"eval_loss": 0.
|
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": 4.
|
45 |
-
"loss": 0.
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
-
"epoch": 0.
|
50 |
-
"eval_loss": 0.
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second": 15.
|
53 |
-
"eval_steps_per_second": 1.
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
-
"epoch": 0.
|
58 |
-
"grad_norm": 0.
|
59 |
-
"learning_rate": 4.
|
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": 4.
|
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": 4.
|
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": 4.
|
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": 4.
|
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": 4.
|
135 |
-
"loss": 0.
|
136 |
"step": 4500
|
137 |
},
|
138 |
{
|
139 |
-
"epoch": 0.
|
140 |
-
"eval_loss": 0.
|
141 |
-
"eval_runtime":
|
142 |
-
"eval_samples_per_second": 15.
|
143 |
-
"eval_steps_per_second": 1.
|
144 |
"step": 4500
|
145 |
}
|
146 |
],
|
147 |
"logging_steps": 500,
|
148 |
-
"max_steps":
|
149 |
"num_input_tokens_seen": 0,
|
150 |
-
"num_train_epochs":
|
151 |
"save_steps": 500,
|
152 |
"stateful_callbacks": {
|
153 |
"TrainerControl": {
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7251659035682678,
|
3 |
+
"best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e4l57-l/checkpoint-4500",
|
4 |
+
"epoch": 0.47994880546075086,
|
5 |
"eval_steps": 500,
|
6 |
"global_step": 4500,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.05332764505119454,
|
13 |
+
"grad_norm": 414.2552795410156,
|
14 |
+
"learning_rate": 4.911120591581342e-07,
|
15 |
+
"loss": 0.3809,
|
16 |
"step": 500
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.05332764505119454,
|
20 |
+
"eval_loss": 1.1109352111816406,
|
21 |
+
"eval_runtime": 63.6734,
|
22 |
+
"eval_samples_per_second": 15.501,
|
23 |
+
"eval_steps_per_second": 1.947,
|
24 |
"step": 500
|
25 |
},
|
26 |
{
|
27 |
+
"epoch": 0.10665529010238908,
|
28 |
+
"grad_norm": 45.880027770996094,
|
29 |
+
"learning_rate": 4.822241183162685e-07,
|
30 |
+
"loss": 0.2649,
|
31 |
"step": 1000
|
32 |
},
|
33 |
{
|
34 |
+
"epoch": 0.10665529010238908,
|
35 |
+
"eval_loss": 0.9588962197303772,
|
36 |
+
"eval_runtime": 62.6825,
|
37 |
+
"eval_samples_per_second": 15.746,
|
38 |
+
"eval_steps_per_second": 1.978,
|
39 |
"step": 1000
|
40 |
},
|
41 |
{
|
42 |
+
"epoch": 0.1599829351535836,
|
43 |
+
"grad_norm": 432.9915466308594,
|
44 |
+
"learning_rate": 4.733361774744027e-07,
|
45 |
+
"loss": 0.2104,
|
46 |
"step": 1500
|
47 |
},
|
48 |
{
|
49 |
+
"epoch": 0.1599829351535836,
|
50 |
+
"eval_loss": 0.90110844373703,
|
51 |
+
"eval_runtime": 62.6757,
|
52 |
+
"eval_samples_per_second": 15.748,
|
53 |
+
"eval_steps_per_second": 1.978,
|
54 |
"step": 1500
|
55 |
},
|
56 |
{
|
57 |
+
"epoch": 0.21331058020477817,
|
58 |
+
"grad_norm": 0.014208819717168808,
|
59 |
+
"learning_rate": 4.6444823663253695e-07,
|
60 |
+
"loss": 0.1849,
|
61 |
"step": 2000
|
62 |
},
|
63 |
{
|
64 |
+
"epoch": 0.21331058020477817,
|
65 |
+
"eval_loss": 0.8570474982261658,
|
66 |
+
"eval_runtime": 63.7296,
|
67 |
+
"eval_samples_per_second": 15.487,
|
68 |
+
"eval_steps_per_second": 1.946,
|
69 |
"step": 2000
|
70 |
},
|
71 |
{
|
72 |
+
"epoch": 0.2666382252559727,
|
73 |
+
"grad_norm": 174.73324584960938,
|
74 |
+
"learning_rate": 4.5556029579067116e-07,
|
75 |
+
"loss": 0.2056,
|
76 |
"step": 2500
|
77 |
},
|
78 |
{
|
79 |
+
"epoch": 0.2666382252559727,
|
80 |
+
"eval_loss": 0.7895939350128174,
|
81 |
+
"eval_runtime": 63.8387,
|
82 |
+
"eval_samples_per_second": 15.461,
|
83 |
+
"eval_steps_per_second": 1.942,
|
84 |
"step": 2500
|
85 |
},
|
86 |
{
|
87 |
+
"epoch": 0.3199658703071672,
|
88 |
+
"grad_norm": 9.852073823424234e-09,
|
89 |
+
"learning_rate": 4.4667235494880547e-07,
|
90 |
+
"loss": 0.159,
|
91 |
"step": 3000
|
92 |
},
|
93 |
{
|
94 |
+
"epoch": 0.3199658703071672,
|
95 |
+
"eval_loss": 0.7647623419761658,
|
96 |
+
"eval_runtime": 63.9155,
|
97 |
+
"eval_samples_per_second": 15.442,
|
98 |
+
"eval_steps_per_second": 1.94,
|
99 |
"step": 3000
|
100 |
},
|
101 |
{
|
102 |
+
"epoch": 0.37329351535836175,
|
103 |
+
"grad_norm": 0.0025215104687958956,
|
104 |
+
"learning_rate": 4.377844141069397e-07,
|
105 |
+
"loss": 0.1696,
|
106 |
"step": 3500
|
107 |
},
|
108 |
{
|
109 |
+
"epoch": 0.37329351535836175,
|
110 |
+
"eval_loss": 0.7638036012649536,
|
111 |
+
"eval_runtime": 63.8003,
|
112 |
+
"eval_samples_per_second": 15.47,
|
113 |
+
"eval_steps_per_second": 1.944,
|
114 |
"step": 3500
|
115 |
},
|
116 |
{
|
117 |
+
"epoch": 0.42662116040955633,
|
118 |
+
"grad_norm": 2.4611830711364746,
|
119 |
+
"learning_rate": 4.2889647326507393e-07,
|
120 |
+
"loss": 0.1125,
|
121 |
"step": 4000
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 0.42662116040955633,
|
125 |
+
"eval_loss": 0.7486374378204346,
|
126 |
+
"eval_runtime": 63.9847,
|
127 |
+
"eval_samples_per_second": 15.426,
|
128 |
+
"eval_steps_per_second": 1.938,
|
129 |
"step": 4000
|
130 |
},
|
131 |
{
|
132 |
+
"epoch": 0.47994880546075086,
|
133 |
+
"grad_norm": 5.230295658111572,
|
134 |
+
"learning_rate": 4.2000853242320814e-07,
|
135 |
+
"loss": 0.1322,
|
136 |
"step": 4500
|
137 |
},
|
138 |
{
|
139 |
+
"epoch": 0.47994880546075086,
|
140 |
+
"eval_loss": 0.7251659035682678,
|
141 |
+
"eval_runtime": 64.4782,
|
142 |
+
"eval_samples_per_second": 15.308,
|
143 |
+
"eval_steps_per_second": 1.923,
|
144 |
"step": 4500
|
145 |
}
|
146 |
],
|
147 |
"logging_steps": 500,
|
148 |
+
"max_steps": 28128,
|
149 |
"num_input_tokens_seen": 0,
|
150 |
+
"num_train_epochs": 3,
|
151 |
"save_steps": 500,
|
152 |
"stateful_callbacks": {
|
153 |
"TrainerControl": {
|
checkpoint-4500/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 sha256:057f6bbf1ff3e34abda0863071bbf5fdcc7edb1102f04dba05c7a15087bc3396
|
3 |
size 4847
|