ramdhanfirdaus commited on
Commit
be6bc28
1 Parent(s): 62f20f4

Training in progress, step 600, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4176108829b074af49b2cbf5e1b5db56126615b9a9ef0d10ffd44d24ae921005
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16b44e49a1aa9e412171f120b14eabb25686a76529babd44a280938bcecbf431
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47e4e1fdc77242198cba37756e1e5633076a59ce7633bdd049c8ccef117014bd
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b31b3fa49212e54d67a9ae8f5b66653d09045e8c1dc35dcd0fb6cf5ec75aafa
3
  size 18902665
last-checkpoint/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 2.475057601928711,
3
  "best_model_checkpoint": "./outputs/checkpoint-600",
4
  "epoch": 0.4371584699453552,
5
  "eval_steps": 100,
@@ -16,80 +16,80 @@
16
  },
17
  {
18
  "epoch": 0.07,
19
- "eval_loss": 2.6424810886383057,
20
- "eval_runtime": 206.4108,
21
- "eval_samples_per_second": 30.396,
22
- "eval_steps_per_second": 3.803,
23
  "step": 100
24
  },
25
  {
26
  "epoch": 0.15,
27
  "learning_rate": 0.0002,
28
- "loss": 2.6061,
29
  "step": 200
30
  },
31
  {
32
  "epoch": 0.15,
33
- "eval_loss": 2.5929574966430664,
34
- "eval_runtime": 206.2177,
35
- "eval_samples_per_second": 30.424,
36
- "eval_steps_per_second": 3.807,
37
  "step": 200
38
  },
39
  {
40
  "epoch": 0.22,
41
  "learning_rate": 0.0002,
42
- "loss": 2.5643,
43
  "step": 300
44
  },
45
  {
46
  "epoch": 0.22,
47
- "eval_loss": 2.5578970909118652,
48
- "eval_runtime": 206.509,
49
- "eval_samples_per_second": 30.381,
50
- "eval_steps_per_second": 3.801,
51
  "step": 300
52
  },
53
  {
54
  "epoch": 0.29,
55
  "learning_rate": 0.0002,
56
- "loss": 2.5383,
57
  "step": 400
58
  },
59
  {
60
  "epoch": 0.29,
61
- "eval_loss": 2.5257716178894043,
62
- "eval_runtime": 206.1349,
63
- "eval_samples_per_second": 30.436,
64
- "eval_steps_per_second": 3.808,
65
  "step": 400
66
  },
67
  {
68
  "epoch": 0.36,
69
  "learning_rate": 0.0002,
70
- "loss": 2.4959,
71
  "step": 500
72
  },
73
  {
74
  "epoch": 0.36,
75
- "eval_loss": 2.5014102458953857,
76
- "eval_runtime": 282.6461,
77
- "eval_samples_per_second": 22.197,
78
- "eval_steps_per_second": 2.777,
79
  "step": 500
80
  },
81
  {
82
  "epoch": 0.44,
83
  "learning_rate": 0.0002,
84
- "loss": 2.4693,
85
  "step": 600
86
  },
87
  {
88
  "epoch": 0.44,
89
- "eval_loss": 2.475057601928711,
90
- "eval_runtime": 205.7759,
91
- "eval_samples_per_second": 30.489,
92
- "eval_steps_per_second": 3.815,
93
  "step": 600
94
  }
95
  ],
 
1
  {
2
+ "best_metric": 2.474956512451172,
3
  "best_model_checkpoint": "./outputs/checkpoint-600",
4
  "epoch": 0.4371584699453552,
5
  "eval_steps": 100,
 
16
  },
17
  {
18
  "epoch": 0.07,
19
+ "eval_loss": 2.6424834728240967,
20
+ "eval_runtime": 206.3704,
21
+ "eval_samples_per_second": 30.402,
22
+ "eval_steps_per_second": 3.804,
23
  "step": 100
24
  },
25
  {
26
  "epoch": 0.15,
27
  "learning_rate": 0.0002,
28
+ "loss": 2.6053,
29
  "step": 200
30
  },
31
  {
32
  "epoch": 0.15,
33
+ "eval_loss": 2.592982053756714,
34
+ "eval_runtime": 206.2608,
35
+ "eval_samples_per_second": 30.418,
36
+ "eval_steps_per_second": 3.806,
37
  "step": 200
38
  },
39
  {
40
  "epoch": 0.22,
41
  "learning_rate": 0.0002,
42
+ "loss": 2.5637,
43
  "step": 300
44
  },
45
  {
46
  "epoch": 0.22,
47
+ "eval_loss": 2.558687448501587,
48
+ "eval_runtime": 206.6302,
49
+ "eval_samples_per_second": 30.363,
50
+ "eval_steps_per_second": 3.799,
51
  "step": 300
52
  },
53
  {
54
  "epoch": 0.29,
55
  "learning_rate": 0.0002,
56
+ "loss": 2.5384,
57
  "step": 400
58
  },
59
  {
60
  "epoch": 0.29,
61
+ "eval_loss": 2.5261261463165283,
62
+ "eval_runtime": 206.3988,
63
+ "eval_samples_per_second": 30.397,
64
+ "eval_steps_per_second": 3.803,
65
  "step": 400
66
  },
67
  {
68
  "epoch": 0.36,
69
  "learning_rate": 0.0002,
70
+ "loss": 2.4965,
71
  "step": 500
72
  },
73
  {
74
  "epoch": 0.36,
75
+ "eval_loss": 2.5020904541015625,
76
+ "eval_runtime": 273.7006,
77
+ "eval_samples_per_second": 22.923,
78
+ "eval_steps_per_second": 2.868,
79
  "step": 500
80
  },
81
  {
82
  "epoch": 0.44,
83
  "learning_rate": 0.0002,
84
+ "loss": 2.4706,
85
  "step": 600
86
  },
87
  {
88
  "epoch": 0.44,
89
+ "eval_loss": 2.474956512451172,
90
+ "eval_runtime": 206.4725,
91
+ "eval_samples_per_second": 30.387,
92
+ "eval_steps_per_second": 3.802,
93
  "step": 600
94
  }
95
  ],
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a0ffd8c2b139f27950886c21bfa338a00634210331df117dcff8cd3df7ce8ad
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3618b713e8d14cca4d31f18e13bbc5304b540d431ee441c88df694b97c28653e
3
  size 4219