kevinoli commited on
Commit
32b3231
1 Parent(s): 9e583d8

Training in progress, step 2500, checkpoint

Browse files
checkpoint-2500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbb5659c510045c12a2d0e6b5a7c1126799a72099382d0ef20d712449da0038a
3
  size 1711848436
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf380baa582bbed391bd13a28758d012c390128502cef9458cb1556cdfe6dcf2
3
  size 1711848436
checkpoint-2500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:374c9ccb99b8f3aa527bf7888a10fcc17db91df5875bce23763ce41cadd92b1b
3
  size 3424043887
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0473a230541487c30e7390db3bb8c803741329821be0ada47619553db8609453
3
  size 3424043887
checkpoint-2500/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 1.1090214252471924,
3
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-l/checkpoint-2500",
4
  "epoch": 0.2666382252559727,
5
  "eval_steps": 500,
@@ -10,77 +10,77 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.05332764505119454,
13
- "grad_norm": 247.07174682617188,
14
  "learning_rate": 9.822241183162683e-08,
15
  "loss": 0.4515,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.05332764505119454,
20
- "eval_loss": 1.38526451587677,
21
- "eval_runtime": 63.6956,
22
- "eval_samples_per_second": 15.496,
23
- "eval_steps_per_second": 1.947,
24
  "step": 500
25
  },
26
  {
27
  "epoch": 0.10665529010238908,
28
- "grad_norm": 72.11767578125,
29
  "learning_rate": 9.64448236632537e-08,
30
- "loss": 0.414,
31
  "step": 1000
32
  },
33
  {
34
  "epoch": 0.10665529010238908,
35
- "eval_loss": 1.284197211265564,
36
- "eval_runtime": 62.7418,
37
- "eval_samples_per_second": 15.731,
38
- "eval_steps_per_second": 1.976,
39
  "step": 1000
40
  },
41
  {
42
  "epoch": 0.1599829351535836,
43
- "grad_norm": 812.2269287109375,
44
  "learning_rate": 9.466723549488054e-08,
45
- "loss": 0.3279,
46
  "step": 1500
47
  },
48
  {
49
  "epoch": 0.1599829351535836,
50
- "eval_loss": 1.2100127935409546,
51
- "eval_runtime": 62.6215,
52
- "eval_samples_per_second": 15.761,
53
- "eval_steps_per_second": 1.98,
54
  "step": 1500
55
  },
56
  {
57
  "epoch": 0.21331058020477817,
58
- "grad_norm": 4.459943771362305,
59
  "learning_rate": 9.288964732650739e-08,
60
  "loss": 0.2912,
61
  "step": 2000
62
  },
63
  {
64
  "epoch": 0.21331058020477817,
65
- "eval_loss": 1.1584910154342651,
66
- "eval_runtime": 64.0453,
67
- "eval_samples_per_second": 15.411,
68
- "eval_steps_per_second": 1.936,
69
  "step": 2000
70
  },
71
  {
72
  "epoch": 0.2666382252559727,
73
- "grad_norm": 328.06475830078125,
74
  "learning_rate": 9.111205915813424e-08,
75
- "loss": 0.3056,
76
  "step": 2500
77
  },
78
  {
79
  "epoch": 0.2666382252559727,
80
- "eval_loss": 1.1090214252471924,
81
- "eval_runtime": 63.2171,
82
- "eval_samples_per_second": 15.613,
83
- "eval_steps_per_second": 1.961,
84
  "step": 2500
85
  }
86
  ],
 
1
  {
2
+ "best_metric": 1.1095446348190308,
3
  "best_model_checkpoint": "./output/clip-finetuned-csu-p14-336-e3l17-l/checkpoint-2500",
4
  "epoch": 0.2666382252559727,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.05332764505119454,
13
+ "grad_norm": 246.1711883544922,
14
  "learning_rate": 9.822241183162683e-08,
15
  "loss": 0.4515,
16
  "step": 500
17
  },
18
  {
19
  "epoch": 0.05332764505119454,
20
+ "eval_loss": 1.3850886821746826,
21
+ "eval_runtime": 63.8439,
22
+ "eval_samples_per_second": 15.46,
23
+ "eval_steps_per_second": 1.942,
24
  "step": 500
25
  },
26
  {
27
  "epoch": 0.10665529010238908,
28
+ "grad_norm": 81.48503875732422,
29
  "learning_rate": 9.64448236632537e-08,
30
+ "loss": 0.4148,
31
  "step": 1000
32
  },
33
  {
34
  "epoch": 0.10665529010238908,
35
+ "eval_loss": 1.284144401550293,
36
+ "eval_runtime": 63.853,
37
+ "eval_samples_per_second": 15.457,
38
+ "eval_steps_per_second": 1.942,
39
  "step": 1000
40
  },
41
  {
42
  "epoch": 0.1599829351535836,
43
+ "grad_norm": 718.367919921875,
44
  "learning_rate": 9.466723549488054e-08,
45
+ "loss": 0.3281,
46
  "step": 1500
47
  },
48
  {
49
  "epoch": 0.1599829351535836,
50
+ "eval_loss": 1.2112621068954468,
51
+ "eval_runtime": 64.127,
52
+ "eval_samples_per_second": 15.391,
53
+ "eval_steps_per_second": 1.934,
54
  "step": 1500
55
  },
56
  {
57
  "epoch": 0.21331058020477817,
58
+ "grad_norm": 4.5923566818237305,
59
  "learning_rate": 9.288964732650739e-08,
60
  "loss": 0.2912,
61
  "step": 2000
62
  },
63
  {
64
  "epoch": 0.21331058020477817,
65
+ "eval_loss": 1.159011960029602,
66
+ "eval_runtime": 63.7062,
67
+ "eval_samples_per_second": 15.493,
68
+ "eval_steps_per_second": 1.946,
69
  "step": 2000
70
  },
71
  {
72
  "epoch": 0.2666382252559727,
73
+ "grad_norm": 319.4483642578125,
74
  "learning_rate": 9.111205915813424e-08,
75
+ "loss": 0.3073,
76
  "step": 2500
77
  },
78
  {
79
  "epoch": 0.2666382252559727,
80
+ "eval_loss": 1.1095446348190308,
81
+ "eval_runtime": 63.9925,
82
+ "eval_samples_per_second": 15.424,
83
+ "eval_steps_per_second": 1.938,
84
  "step": 2500
85
  }
86
  ],
checkpoint-2500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b52c451dc1fefed1a64b0a23a69d323685c58d3023f0abb7cb18bc82e1be68c7
3
  size 4847
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52c8db40c27633302368150be011282e1650a78d29cdfc5e366df6966e8e6c70
3
  size 4847